基于免疫多词主体自治学习的情感分析研究
|
摘要
情感文本指作者对人或物或事做出的有情感极性的评论性文本，其中情感信息包含评价持有者、评价对象、评价词，以及修饰成分，它反映了人们对事物的态度。文本情感分析指借助自然语言处理技术从情感文本中识别和获取情感信息的方法。但由于词的情感极性受上下文影响而难以准确判定，评价对象和评价词之间难以建立准确的对应关系，以及情感表达方式的多样性等因素，文本情感分析研究面临巨大挑战。近年来，大量学者针对词汇、短语、句子，以及篇章等不同粒度的情感文本展开研究，并尝试借助它提高产品推荐、自动问答，以及信息检索等系统的性能。
基于统计机器学习的文本情感分析尽管作为主流情感分析方法受到广泛关注，但存在需要大规模标注语料用于模型的训练和评价以及无法通过持续学习提升性能等缺点。本文尝试借助适应性免疫原理构建新的机器学习模型克服上述缺点。首先，本文提出判断词汇和句子情感极性的半监督学习模型，尽管提高了挖掘情感词和句的精度，但也进一步暴露出基于统计机器学习的情感分析的不足，这成为构建新的机器学习模型的出发点；然后，受人体免疫系统与人类语言系统的相似性启发，构建基于适应性免疫原理的自治机器学习模型。借助浆细胞负向调节机制构建基于多主体复杂系统建模的人工免疫系统，搭建模型基础平台，进而通过将词汇模拟为参与免疫反应的细胞和分子构建多词主体自治机器学习模型；最后，借助该模型实现情感要素分析。主要研究内容包括以下四个方面：
1.在基于统计机器学习的情感分析研究方面，提出基于集合相似并的半监督情感分析模型。该模型以情感流图为基础，首先，获取情感候选对象，进而借助情感词典构建情感流图，图中节点是候选情感词或者句子，而边包括两种：节点之间的语义关系以及节点的初始情感极性；然后，借助Ford-Fulkerson算法将该流图分割为子图；最后，借助集合相似并方法将所有子图中的节点合并为积极和消极两个情感集合，实现节点的情感极性判断，并且结合基于自训练的半监督模型进一步提高情感分析性能。
2.在构建模型基础平台研究方面，提出基于浆细胞负向调节机制的人工免疫系统。浆细胞负向调节机制指出浆细胞可以与T细胞结合进而使T细胞死亡，实现负向调节T细胞种群的多样性，从而提高T细胞与B细胞交互效率，进而提高适应性免疫反应的效率。以克隆选择原理、负选择原理、独特型免疫网络原理，以及浆细胞负反馈机制为理论基础，以基于元胞自动机的多主体复杂系统建模为建模方法，将参与适应性反应的免疫细胞和分子模拟为主体构建人工免疫系统，实验表明该模型不仅能够实现对适应性免疫反应较真实的模拟，而且验证了浆细胞负向调节机制有效性。
3.在新的机器学习模型研究方面，提出基于适应性免疫原理的多词主体自治学习模型。以适应性免疫原理为理论基础，以面向自治计算的多主体复杂系统建模为建模方法，将词汇模拟为参与适应性免疫反应的细胞和分子，词汇之间的关系模拟为免疫细胞或分子的受体之间的特异性关系，关系强度为受体间的亲和度来构建免疫词主体。在适应性免疫反应中，通过在免疫词主体的交互、克隆、变异和选择行为作用下，进行免疫词主体自治学习。在不断学习作用下，达到优化词主体间特异性关系（即词汇关系）的目的。
4.在以上工作基础上，提出基于多词主体自治学习模型的情感要素分析模型。首先，构建情感要素分析目标函数。其次，将词汇模拟为参与适应性免疫反应的B细胞和抗原，通过模拟B细胞和抗原的受体、行为、状态、以及交互策略构建免疫词主体；最后，在适应性免疫原理作用下通过不断的免疫反应优化词汇之间的关系，进而实现优化评价对象和评价词之间的关系，达到提升优化目标函数的目的。
综上所述，本文致力于通过模拟免疫细胞和分子在特异性免疫反应中的行为、状态，以及策略，进而基于适应性免疫原理构建多词主体自治机器学习模型，并将其用于克服现有文本情感分析方法的缺点，取得了一些初步的研究成果。随着该模型的进一步研究以及新的免疫原理的不断发现，相信基于适应性免疫原理的多词主体自治机器学习模型的研究在未来会取得更大的突破。
Sentiment texts refer to comments on persons, things, or events with sentimentpolarities. Sentiment information in these comments reflecting people’s attitudescontain evaluation holders, evaluation objects, evaluation words, and their modifiers.Sentiment analysis on sentiment texts refers methods to identifying and extractingsentiment information from sentiment texts with Natural Language Processingtechnologies. However, characteristics of sentiment texts give a challenge to thesentiment analysis on sentiment texts. For example, firstly, sentiment polarities ofwords affected by contents cannot be judged accurately. Secondly, it is difficult toconstruct accurate relations between evaluation objects and evaluation words.Finally, sentiment expressions are various. In recent years, many researchers havecarried out research of sentiment analysis on texts at different levels such as words,phrases, sentences, and texts and tried to apply it to Product Recommendation (PR),Question Answering (QA), and Information Retrieval (IR) to improve performance.
Although statistical machine learning based sentiment analysis on texts attractsextensive attention as the mainstream approaches, there are still deficiencies of theseapproaches. Firstly, the large-scale labeled corpus is required for training andevaluating models. Then, these models cannot learn continuously to improve theirperformance. An adaptive immune theories based machine learning model ispresented to overcome these two deficiencies. A semi-supervised model based onset-similarity joins is presented to mine sentiment words and sentences. Althoughaccuracies of mining sentiment words and sentences were improved, it revealeddeficiencies of statistical machine learning based sentiment analysis models fully,where overcoming these deficiencies became aims of constructing the new machinelearning model; Then, inspired by similarities between the human immune systemand the human language system, an autonomy learning model is presented based onadaptive immune theories, which included two steps:(1) the artificial immunesystem based on multi-agent system modeling is constructed with the plasmanegative regulation mechanism as the foundation platform for constructing the newmachine learning model;(2) a multi-word-agent autonomy learning model isconstructed through simulating words as immune cellular and molecular to optimizerelations between words by interactions between immune word-agents; Finally,sentiment analysis on collocations is realized by the autonomy learning model; Themain contents of our research work include four aspects as follows.
Firstly, in the research of sentiment analysis based on statistical machinelearning methods, set-similarity joins based semi-supervised sentiment analysis is presented. The model is built based on the flow graph of sentiment candidates.Firstly, sentiment candidates are extracted from corpus and used to construct theflow graph with a sentiment lexicon, where nodes in the graph are these candidates,and edges are semantic relations between candidates and primary sentimentpolarities. Then the graph is cut into sub-graphs with the Ford-Fulkerson algorithm.Finally nodes in these sub-graphs can be merged into positive and negative sets byset-similarity joins. And the performance is improved further by the self-trainingbased semi-supervised method.
Secondly, in the research of constructing the foundation platform, the plasmanegative regulation mechanism based artificial immune system is proposed. Plasmacan bind T cells to kill them so as to reduce the diversity of the T cells population,which improves the efficiency of interactions between T cells and B cells in order toimprove the efficiency of immune responses. An artificial immune system isconstructed by simulating immune cells and molecular as agents with theories suchas clonal selection, negative selection, idiotypic immune network, and the plasmanegative regulation mechanism and the cellular automaton based complex systemmodeling method. Experimental results show that not only processes of adaptiveimmune responses can be simulated, but also plasma negative regulation mechanismcan improve efficiencies of these responses.
Thirdly, in the research of constructing the new machine learning model, wepresent the adaptive immune theories based multi-word-agent autonomy learningmodel. Words are simulated as immune cells and molecular to construct immuneword-agents with adaptive immune theories and autonomy oriented computingbased complex system modeling, where relations between words are simulated asspecific relations between receptors of these cells and molecular, and strengths ofthese relations are measured by matched degrees called affinities of these receptors.These immune word-agents can learn continuously to optimize relations betweenwords through communicating among them, cloning, mutating, and selecting.
Finally, on the basic of all above researches, we adopt the multi-word-agentautonomy learning model to realize sentiment analysis on collocations. Firstly, thesystem object function for sentiment analysis on collocations is constructed. Thenwords are simulated as B cells and antigens involved in adaptive immune responses,and immune word-agents are built by simulating behaviors, states, and interactivepolicies of B cells and antigens. Finally, relations between words are optimized byadaptive immune responses so as to optimize relations between evaluation objectsand evaluation words continuously, which is to optimize the object function.
In conclusion, the main object of our research is to construct an autonomylearning model based on adaptive immune theories through simulating behaviors,states, and policies of immune cells and molecular in adaptive immune responses, and the model is applied to overcoming deficiencies of present sentiment analysismodels. This research has achieved some preliminary results. We believe that thedeep research on the model and discoveries of immune theories can promote thedevelopment of the model in the future.
基于统计机器学习的文本情感分析尽管作为主流情感分析方法受到广泛关注，但存在需要大规模标注语料用于模型的训练和评价以及无法通过持续学习提升性能等缺点。本文尝试借助适应性免疫原理构建新的机器学习模型克服上述缺点。首先，本文提出判断词汇和句子情感极性的半监督学习模型，尽管提高了挖掘情感词和句的精度，但也进一步暴露出基于统计机器学习的情感分析的不足，这成为构建新的机器学习模型的出发点；然后，受人体免疫系统与人类语言系统的相似性启发，构建基于适应性免疫原理的自治机器学习模型。借助浆细胞负向调节机制构建基于多主体复杂系统建模的人工免疫系统，搭建模型基础平台，进而通过将词汇模拟为参与免疫反应的细胞和分子构建多词主体自治机器学习模型；最后，借助该模型实现情感要素分析。主要研究内容包括以下四个方面：
1.在基于统计机器学习的情感分析研究方面，提出基于集合相似并的半监督情感分析模型。该模型以情感流图为基础，首先，获取情感候选对象，进而借助情感词典构建情感流图，图中节点是候选情感词或者句子，而边包括两种：节点之间的语义关系以及节点的初始情感极性；然后，借助Ford-Fulkerson算法将该流图分割为子图；最后，借助集合相似并方法将所有子图中的节点合并为积极和消极两个情感集合，实现节点的情感极性判断，并且结合基于自训练的半监督模型进一步提高情感分析性能。
2.在构建模型基础平台研究方面，提出基于浆细胞负向调节机制的人工免疫系统。浆细胞负向调节机制指出浆细胞可以与T细胞结合进而使T细胞死亡，实现负向调节T细胞种群的多样性，从而提高T细胞与B细胞交互效率，进而提高适应性免疫反应的效率。以克隆选择原理、负选择原理、独特型免疫网络原理，以及浆细胞负反馈机制为理论基础，以基于元胞自动机的多主体复杂系统建模为建模方法，将参与适应性反应的免疫细胞和分子模拟为主体构建人工免疫系统，实验表明该模型不仅能够实现对适应性免疫反应较真实的模拟，而且验证了浆细胞负向调节机制有效性。
3.在新的机器学习模型研究方面，提出基于适应性免疫原理的多词主体自治学习模型。以适应性免疫原理为理论基础，以面向自治计算的多主体复杂系统建模为建模方法，将词汇模拟为参与适应性免疫反应的细胞和分子，词汇之间的关系模拟为免疫细胞或分子的受体之间的特异性关系，关系强度为受体间的亲和度来构建免疫词主体。在适应性免疫反应中，通过在免疫词主体的交互、克隆、变异和选择行为作用下，进行免疫词主体自治学习。在不断学习作用下，达到优化词主体间特异性关系（即词汇关系）的目的。
4.在以上工作基础上，提出基于多词主体自治学习模型的情感要素分析模型。首先，构建情感要素分析目标函数。其次，将词汇模拟为参与适应性免疫反应的B细胞和抗原，通过模拟B细胞和抗原的受体、行为、状态、以及交互策略构建免疫词主体；最后，在适应性免疫原理作用下通过不断的免疫反应优化词汇之间的关系，进而实现优化评价对象和评价词之间的关系，达到提升优化目标函数的目的。
综上所述，本文致力于通过模拟免疫细胞和分子在特异性免疫反应中的行为、状态，以及策略，进而基于适应性免疫原理构建多词主体自治机器学习模型，并将其用于克服现有文本情感分析方法的缺点，取得了一些初步的研究成果。随着该模型的进一步研究以及新的免疫原理的不断发现，相信基于适应性免疫原理的多词主体自治机器学习模型的研究在未来会取得更大的突破。
Sentiment texts refer to comments on persons, things, or events with sentimentpolarities. Sentiment information in these comments reflecting people’s attitudescontain evaluation holders, evaluation objects, evaluation words, and their modifiers.Sentiment analysis on sentiment texts refers methods to identifying and extractingsentiment information from sentiment texts with Natural Language Processingtechnologies. However, characteristics of sentiment texts give a challenge to thesentiment analysis on sentiment texts. For example, firstly, sentiment polarities ofwords affected by contents cannot be judged accurately. Secondly, it is difficult toconstruct accurate relations between evaluation objects and evaluation words.Finally, sentiment expressions are various. In recent years, many researchers havecarried out research of sentiment analysis on texts at different levels such as words,phrases, sentences, and texts and tried to apply it to Product Recommendation (PR),Question Answering (QA), and Information Retrieval (IR) to improve performance.
Although statistical machine learning based sentiment analysis on texts attractsextensive attention as the mainstream approaches, there are still deficiencies of theseapproaches. Firstly, the large-scale labeled corpus is required for training andevaluating models. Then, these models cannot learn continuously to improve theirperformance. An adaptive immune theories based machine learning model ispresented to overcome these two deficiencies. A semi-supervised model based onset-similarity joins is presented to mine sentiment words and sentences. Althoughaccuracies of mining sentiment words and sentences were improved, it revealeddeficiencies of statistical machine learning based sentiment analysis models fully,where overcoming these deficiencies became aims of constructing the new machinelearning model; Then, inspired by similarities between the human immune systemand the human language system, an autonomy learning model is presented based onadaptive immune theories, which included two steps:(1) the artificial immunesystem based on multi-agent system modeling is constructed with the plasmanegative regulation mechanism as the foundation platform for constructing the newmachine learning model;(2) a multi-word-agent autonomy learning model isconstructed through simulating words as immune cellular and molecular to optimizerelations between words by interactions between immune word-agents; Finally,sentiment analysis on collocations is realized by the autonomy learning model; Themain contents of our research work include four aspects as follows.
Firstly, in the research of sentiment analysis based on statistical machinelearning methods, set-similarity joins based semi-supervised sentiment analysis is presented. The model is built based on the flow graph of sentiment candidates.Firstly, sentiment candidates are extracted from corpus and used to construct theflow graph with a sentiment lexicon, where nodes in the graph are these candidates,and edges are semantic relations between candidates and primary sentimentpolarities. Then the graph is cut into sub-graphs with the Ford-Fulkerson algorithm.Finally nodes in these sub-graphs can be merged into positive and negative sets byset-similarity joins. And the performance is improved further by the self-trainingbased semi-supervised method.
Secondly, in the research of constructing the foundation platform, the plasmanegative regulation mechanism based artificial immune system is proposed. Plasmacan bind T cells to kill them so as to reduce the diversity of the T cells population,which improves the efficiency of interactions between T cells and B cells in order toimprove the efficiency of immune responses. An artificial immune system isconstructed by simulating immune cells and molecular as agents with theories suchas clonal selection, negative selection, idiotypic immune network, and the plasmanegative regulation mechanism and the cellular automaton based complex systemmodeling method. Experimental results show that not only processes of adaptiveimmune responses can be simulated, but also plasma negative regulation mechanismcan improve efficiencies of these responses.
Thirdly, in the research of constructing the new machine learning model, wepresent the adaptive immune theories based multi-word-agent autonomy learningmodel. Words are simulated as immune cells and molecular to construct immuneword-agents with adaptive immune theories and autonomy oriented computingbased complex system modeling, where relations between words are simulated asspecific relations between receptors of these cells and molecular, and strengths ofthese relations are measured by matched degrees called affinities of these receptors.These immune word-agents can learn continuously to optimize relations betweenwords through communicating among them, cloning, mutating, and selecting.
Finally, on the basic of all above researches, we adopt the multi-word-agentautonomy learning model to realize sentiment analysis on collocations. Firstly, thesystem object function for sentiment analysis on collocations is constructed. Thenwords are simulated as B cells and antigens involved in adaptive immune responses,and immune word-agents are built by simulating behaviors, states, and interactivepolicies of B cells and antigens. Finally, relations between words are optimized byadaptive immune responses so as to optimize relations between evaluation objectsand evaluation words continuously, which is to optimize the object function.
In conclusion, the main object of our research is to construct an autonomylearning model based on adaptive immune theories through simulating behaviors,states, and policies of immune cells and molecular in adaptive immune responses, and the model is applied to overcoming deficiencies of present sentiment analysismodels. This research has achieved some preliminary results. We believe that thedeep research on the model and discoveries of immune theories can promote thedevelopment of the model in the future.
引文
[1] Conrad J and Schilder F. Opinion Mining in Legal Blogs [C]. In Proceedings ofthe International Conference on Artificial Intelligence and Law (ICAIL),2007:231-236.
[2] Horrigan J. Online shopping [R]. Pew Internet&American Life Project Report,2008.
[3] Zabin J and Jefferies A. Social Media Monitoring and Analysis: GeneratingConsumer Insights from Online Conversation [R]. Aberdeen Group BenchmarkReport,2008.
[4] Taboada M, Brooke J, Tofiloski M, et al. Lexicon-Based Methods forSentiment Analysis [J]. Computational Linguistics,37(2),2011:267-307.
[5] Tetsuya N and Yi J. Sentiment Analysis: Capturing Favorability Using NaturalLanguage Processing [C]. In Proceedings of the KCAP-03,2nd Intl. Conf. onKnowledge Capture,2003:70-77.
[6] Terveen L, Hill W, Amento B, et al. PHOAKS: A System for SharingRecommendations. Communications of the Association for ComputingMachinery (CACM),40(3),1997:59-62.
[7] Lita L, Schlaikjer A, Hong W, and Nyberg E. Qualitative Dimensions inQuestion Answering: Extending the Definitional QA task [C]. In Proceedingsof AAAI,2005:1616-1617.
[8] Somasundaran S, Wilson T, Wiebe J, et al. QA with Attitude: ExploitingOpinion Type Analysis for Improving Question Answering in On-lineDiscussions and the News [C]. In Proceedings of the International Conferenceon Weblogs and Social Media (ICWSM),2007.
[9] Stoyanov V, Cardie C, and Wiebe J. Multi-perspective Question AnsweringUsing the OpQA Corpus [C]. In Proceedings of the Human LanguageTechnology Conference and the Conference on Empirical Methods in NaturalLanguage Processing (HLT/EMNLP),2005:923-930.
[10] Seki Y, Eguchi Y, Kando N, et al. Multi-document Summarization withSubjectivity Analysis at DUC2005[C]. In Proceedings of the DocumentUnderstanding Conference (DUC),2005.
[11] Abbasi A. Affect Intensity Analysis of Dark Web Forums [C]. In Proceedingsof Intelligence and Security Informatics (ISI),2007:282-288.
[12] Yu, X., Liu, Y., Huang, X., An, A. Mining Online Reviews for Predicting SalesPerformance: A Case Study in the Movie Domain [J]. IEEE Trans. Knowl.Data Eng.2012:720-734.
[13] Pang B, Lee L, and Vaithyanathan S. Thumbs up? Sentiment Classificationusing Machine Learning Techniques [C]. In Proceedings of Empirical Methodson Natural Language Processing,2002:79-86.
[14] Pang B and Lee L. A Sentimental Education: Sentiment Analysis UsingSubjectivity Summarization Based on Minimum Cuts [C]. In Proceedings ofthe42nd Annual Meeting on Association for Computational Linguistics,2004:271-278.
[15]许洪波,姚天昉,黄萱菁.第二届中文倾向性分析评测技术报告[C].第二届中文倾向性分析评测(The Second Chinese Opinion Analysis Evaluation2009, COAE2009),2009:1-23.
[16] Pang B and Lee L. Opinion Mining and Sentiment Analysis [J]. Foundationsand Trends in Information Retrieval,2(1-2),2008:1-135.
[17] Kim S and Hovy E. Determining the Sentiment of Opinions [C]. InProceedings of COLING,2004:1367-1373.
[18] Mao Y and Lebanon G. Isotonic Conditional Random Fields and LocalSentiment Flow [C]. In Proceedings of NIPS,2006:961-968.
[19] Abbasi A, France S, Zhang Z, et al. Selecting Attributes for SentimentClassification Using Feature Relation Networks [J]. IEEE Transactions onKnowledge and Data Engineering,23(3),2011:447-462.
[20] Tan C, Lee L, Tang J, et al. User-level Sentiment Analysis Incorporating SocialNetworks [C]. In Proceedings of the17th ACM SIGKDD InternationalConference on Knowledge Discovery and Data Mining,2011:1397-1405.
[21] Mohtarami M, Amiri H, Lan M, et al. Predicting the Uncertainty of SentimentAdjectives in Indirect Answers [C]. In Proceedings of the20th ACMInternational Conference on Information and Knowledge Management,2011:2485-2488.
[22] Qin B, Zhao Y, Gao L, et al. Recommended or Not? Give advice on OnlineProduct [C]. Fifth international conference on Fuzzy Systems and KnowledgeDiscovery,2008:208-212.
[23] Thelwall M, Buckley K, and Paltoglou G. Sentiment in Twitter Events [J].Journal of the American Society for Information Science and Technology,62(2),2011:406-418.
[24]王中卿,李寿山,朱巧明等.基于不平衡数据的中文情感分类[J].中文信息学报,26（3），2012:33-37.
[25] Yan L and Zhang Y. News Sentiment Analysis Based on Cross-DomainSentiment Word Lists and Content Classifiers [C]. Advanced Data Mining andApplications, Lecture Notes in Computer Science Volume7713,2012:577-588.
[26] Glorot X, Bordes A, and Bengio Y. Domain Adaptation for Large-ScaleSentiment Classification: A Deep Learning Approach [C]. In Proceedings ofthe Twenty-eight International Conference on Machine Learning,2011:513-520.
[27] Jerne N. THE GENERATIVE GRAMMAR OF THE IMMUNE SYSTEM [R].Nobel lecture,8December,1984.
[28]宋晓雷,王素格,李红霞等.基于概率潜在语义分析的词汇情感倾向判别[J].中文信息学报,25(2),2011:89-93.
[29] Wu Y and Wen M. Disambiguating Dynamic Sentiment Ambiguous Adjectives
[C]. Proceeding COLING '10Proceedings of the23rd International Conferenceon Computational Linguistics,2010:1191-1199.
[30] Hassan A and Radev D. Identifying Text Polarity Using Random Walks [C].Proceeding ACL '10Proceedings of the48th Annual Meeting of theAssociation for Computational Linguistics,2010:395-403.
[31] Das D and Bandyopadhyay S. Word to Sentence Level Emotion Tagging forBengali Blogs [C]. Proceeding ACL Short '09Proceedings of the ACL-IJCNLP2009Conference Short Papers,2009:149-152.
[32] Rao D and Ravichandran D. Semi-Supervised Polarity Lexicon Induction [C].Proceedings of the12th Conference of the European Chapter of the ACL,2009:675-682.
[33] Blum A, Lafferty J, Rwebangira M R, et al. Semi-supervised Learning UsingRandomized Mincuts [C]. In Proceedings of the ICML,2004.
[34] Zhu X and Ghahramani Z. Learning from Labeled and Unlabeled Data withLabel Propagation [R]. Technical Report CMU-CALD-02-107, CarnegieMellon University.2002.
[35] Fu G and Wang X. Chinese Sentence-level Sentiment Classification based onFuzzy Sets [C]. Proceeding COLING '10Proceedings of the23rd InternationalConference on Computational Linguistics,2010:312-319.
[36] Meena A and Prabhakar T V. Sentence Level Sentiment Analysis in thePresence of Conjuncts Using Linguistic Analysis [J]. Advances in InformationRetrieval, vol.4425. Berlin, Heidelberg: Springer Berlin Heidelberg,2007:573-580.
[37] Xia R and Zong C. Exploring the Use of Word Relation Features for SentimentClassification [C]. Proceeding COLING '10Proceedings of the23rdInternational Conference on Computational Linguistics,2010:1336-1344.
[38] Davidov D, Tsur O, and Rappoport A. Enhanced Sentiment Learning UsingTwitter Hashtags and Smileys [C]. Proceedings of the23rd InternationalConference on Computational Linguistics,2010:241-249.
[39] Wei W and Gulla J A. Sentiment Learning on Product Reviews via SentimentOntology Tree [C]. Proceeding ACL '10Proceedings of the48th AnnualMeeting of the Association for Computational Linguistics,2010:404-413.
[40] Jang H and Shin H. Language-specific Sentiment Analysis in MorphologicallyRich Languages [C]. Proceeding COLING '10Proceedings of the23rdInternational Conference on Computational Linguistics, Aug,2010:498-506.
[41] Zhang Q, Wu Y, Li T, et al. Mining Product Reviews based on ShallowDependency Parsing [C]. In Proceedings of the32nd international ACM SIGIRconference on Research and development in information retrieval,2009:726-727.
[42]王根,赵军.基于多重标记CRF句子情感分析的研究[C].全国第九届计算机语言学学术会议.2007.
[43] Guo H, Zhu H, Guo Z, et al. Domain Customization for Aspect-orientedOpinion Analysis with Multi-level Latent Sentiment Clues [C]. In Proceedingsof the20th ACM International Conference on Information and KnowledgeManagement,2011:2493-2496.
[44] Wei B and Pal C. Cross Lingual Adaptation: An Experiment on SentimentClassifications [C]. Proceeding ACL Short’10Proceedings of the ACL2010Conference Short Papers,2010:258–262.
[45] Socher R, Pennington J, Huang E H, et al. Semi-supervised RecursiveAuto-encoders for Predicting Sentiment Distributions [C]. Proceedings of the2011Conference on Empirical Methods in Natural Language Processing,2011:151-161.
[46] Taboada M, Brooke J, Tofiloski M, et al. Lexicon-Based Methods forSentiment Analysis [J]. Computational Linguistics,37(20),2011:267-307.
[47] Andrew L. M, Raymond E. D, Peter T. P, et al. Learning Word Vectors forSentiment Analysis [C]. In Proceedings of the49th Annual Meeting of theAssociation for Computational Linguistics: Human Language Technologies,2011:142-150.
[48] Tan S and Wang Y. Weighted SCL Model for Adaptation of SentimentClassification [J]. Expert Systems with Applications,38(8),2011:10524-10531.
[49] Wu Q, Tan S, Cheng X, et al. MIEA: a Mutual Iterative EnhancementApproach for Cross-Domain Sentiment Classification [C]. Coling2010Posters,2010:1327-1335.
[50] Agarwal A, Xie B, Vovsha I, et al. Sentiment Analysis of Twitter Data [C].Proceeding LSM '11Proceedings of the Workshop on Languages in SocialMedia, Jun,2011:30-38.
[51] Balamurali A, Joshi A, and Bhattacharyya P. Harnessing WordNet Senses forSupervised Sentiment Classification [C]. EMNLPACL,2011:1081-1091.
[52] Li S, Lee S Y M, Chen Y, et al. Sentiment Classification and Polarity Shifting
[C]. Proceeding COLING '10Proceedings of the23rd International Conferenceon Computational Linguistics, Aug,2010:635-643.
[53] Paltoglou G and Thelwall M. A Study of Information Retrieval WeightingSchemes for Sentiment Analysis [C]. Proceeding ACL '10Proceedings of the48th Annual Meeting of the Association for Computational Linguistics, Jul,2010:1386-1395.
[54] Li S, Xia R, Zong C, and Huang C. A Framework of Feature Selection Methodsfor Text Categorization [C]. Proceeding ACL '09Proceedings of the JointConference of the47th Annual Meeting of the ACL and the4th InternationalJoint Conference on Natural Language Processing of the AFNLP,2009:692-700.
[55] Abbasi A, Chen H, and Salem A. Sentiment Analysis in Multiple Languages [J].ACM Transactions on Information Systems,26(3),2008:1-34.
[56] McDonald R, Hannan K, Neylon T, et al. Structured Models for Fine-to-CoarseSentiment Analysis [C]. Proceedings of the Association for ComputationalLinguistics,2007:432-439.
[57]徐琳宏,林鸿飞,杨志豪.基于语义理解的文本倾向性识别机制[J].中文信息学报,21(1),2007:96-100
[58] Wang S, Wei Y, Li D, et al. A Hybrid Method of Feature Selection for ChineseText Sentiment Classification [C]. In Fourth International Conference onFuzzy Systems and Knowledge Discovery,2007:435-439.
[59] Wan X. Bilingual Co-Training for Sentiment Classification of Chinese ProductReviews [J]. Computational Linguistics,37(3),2011:587-616.
[60] Tan C, Lee L, Tang J, et al. User-level Sentiment Analysis Incorporating SocialNetworks [C]. In Proceedings of the17th ACM SIGKDD internationalconference on Knowledge discovery and data mining,2011:1397-1405.
[61] Forrest S, Perelson A, Allen L, et al. Self-nonself Discrimination in aComputer [C]. In Proceedings of the1994IEEE Symposium on Research inSecurity and Privacy,1994:202-212.
[62] Dasgupta D and Forrest S. An Anomaly Detection Algorithm Inspired by theImmune System [J]. Artificial Immune System and Their Applications,57,1999:262-277.
[63] Dasgupta D, Yu S, and Nino F. Recent Advances in Artificial Immune Systems:Models and Applications [J]. Applied Soft Computing,11(2),2011:1574-1587.
[64] Luo W, Wang J, and Wang X. Evolutionary Negative Selection Algorithms forAnomaly Detection [C], In8th Joint Conference on Information Science(JCIS2005),2005.
[65] Luo W, Guo P, and Wang X. On Convergence of Evolutionary NegativeSelection Algorithms for Anomaly Detection [C]. In IEEE Congress onEvolutionary Computation (CEC)(IEEE World Congress on ComputationalIntelligence),2008:2933-2939.
[66] Xu B, Luo W, Pei X, et al. On Average Time Complexity of EvolutionaryNegative Selection Algorithms for Anomaly Detection [C]. In2009WorldSummit on Genetic and Evolutionary Computation (2009GEC Summit),2009.
[67] Zhanga Y, Luo W, Zhang Z, et al. A Hardware/Software Partitioning Algorithmbased on Artificial Immune Principles [J]. Applied Soft Computing,2008:383-391.
[68] Dasgupta D, KrishnaKumar K, Wong D, et al. Negative Selection Algorithmfor Aircraft Fault Detection [C]. In G. Nicosia et al.(Eds), Proceedings ofThird International Conference on Artificial Immune Systems (ICARIS2004),2004:1-13.
[69] Gan Z, Zhao M B, and Chow T W S. Induction Machine Fault Detection UsingClone Selection Programming [J]. Expert System with Applications,34(4),2009:8000-8012.
[70] Dasgupta D and Gonzalez F. An Immunity-based Technique to CharacterizeIntrusions in Computer Networks [J]. IEEE Transactions on EvolutionaryComputation,6(3),2002:281-291.
[71] Jerne N K. Towards a network theory of the immune system [J]. Annalesd’immunologie,125C (1-2),1974:373–389.
[72] Ishida Y. Fully distributed diagnosis by PDP learning algorithm: towardsimmune network PDP model [C]. IEEE International Joint Conference onNeural Networks,1990.
[73] Farmer J D, Packard N H, and Perelson A S. The immune system, adaptation,and machine learning [J]. Physica D: Nonlinear Phenomena,22(1-3),1986:187-204.
[74] Ou C M and Ou C R. Immune Network and Immune Memory Mechanism:Perspectives on Dynamical Systems [C]. In2011International Conference onTechnologies and Applications of Artificial Intelligence,2011:313-318.
[75] Madi A, Kenett D Y, Bransburg-Zabary S, et al. Network Theory Analysis ofAntibody-Antigen Reactivity Data: The Immune Trees at Birth and Adulthood[J]. PLoS ONE,6(3),2011:1-11.
[76] Souza-e-Silva H and dos Santos R M Z. Is the Immune Network a ComplexNetwork? arXiv.org,2012:1-10.
[77] Coelho G, Von Zuben F, Takahashi R, et al. A Concentration-Based ArtificialImmune Network for Multi-objective Optimization [J]. EvolutionaryMulti-Criterion Optimization,6576,2011:343-357.
[78] Gong M, Jiao L, Yang J, and Liu F. Lamarckian Learning in Clonal SelectionAlgorithm for Numerical Optimization [J]. International Journal on ArtificialIntelligence Tools,19(1),2010:19-37.
[79] Gong M, Jiao L, and Zhang L. Baldwinian Learning in Clonal SelectionAlgorithm for Optimization [J]. Information Sciences,180(8),2010:1218-1236.
[80] Tiwari M K, Prakash Kumar A, and Mileham AR. Determination of an OptimalAssembly Sequence Using the PsychoCA [J]. Journal of EngineeringManufacture,2005:137-149
[81] Maier N R F. Psychology in Industry [M].3rd edition,1965:417-419.
[82] Liu X, Shi L, Chen R, and Chen H. A Novel Clonal Selection Algorithm forGlobal Optimization Problems [C]. In International conference on informationengineering and computer science,2009:1-4.
[83] Yang J, Sun L, Lee H P, et al. Clonal Selection based Memetic Algorithm forJob Shop Scheduling Problems [J]. Journal of Bionic Engineering,5(2),2008:111-119.
[84] Garain U, Chakraborty M P, and Dasgupta D. Recognition of HandwrittenIndict Script Using Clonal Selection Algorithm [C]. In Proceedings of the5thinternational conference on Artificial Immune Systems (ICARIS'06),2006:256-266.
[85] Moghaddam M Z and Kardan A. Clonal Selection Algorithm for Partitioningand Scheduling of Codesign Systems [C]. In5th International colloquium onsignal processing and its applications,2009:267-272.
[86] Dai H and Li C. Chaotic Immune Clonal Selection Algorithm and itsApplication [C]. In Proceedings of the2nd international symposium onknowledge acquisition and modeling (KAM2009),2009:65-68.
[87] Gao X Z, Wang X, and Ovaska S J. Fusion of Clonal Selection Algorithm andDifferential Evolution Method in Training Cascade-correlation NeuralNetwork [J]. Neurocomputing,72(10-12),2009:2483-2490.
[88] Li D and Chen Z. SVM Optimized by Immune Clonal Selection Algorithm forFault Diagnostics [C]. In Proceedings Pacific-Asia conference on circuits,communications and systems (PACCS2009),2009:702-705.
[89] Yong L and Sunjun L. A Hybrid Model for Solving TSP based on ArtificialImmune and Ant Colony [C]. In International conference on informationengineering and computer science (ICIECS2009),2009:605-609.
[90] Rocha L M. Complex Systems Modeling: Using Metaphors From Nature inSimulation and Scientific Models. BITS: Computer and CommunicationsNews [R]. Computing, Information, and Communications Division. LosAlamos National Laboratory.1999.
[91] Wolfram S. Cellular Automata as Models of Complexity [J]. Nature,311,1984:419-424.
[92] Liu J, Jin X, and Tsui K C. Autonomy-Oriented Computing (AOC):Formulating Computational Systems With Autonomous Components [J]. IEEETRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS-PART A:SYSTEMS AND HUMANS,35(6),2005:879-902.
[93] Liu J. Autonomy-Oriented Computing (AOC): Formulating ComputationalSystems With Autonomous Components [C]. In Proceedings of the fourthinternational conference on natural computation (Keynote talk),2008:3-11.
[94] Liu J, Zhang S, and Yang J. Characterizing Web Usage Regularities withInformation Foraging Agents [J]. IEEE Transactions on Knowledge and DataEngineering,16(5),2004:566-584.
[95] Zhang S and Liu J. From Local Behaviors to the Dynamics in an AgentNetwork [C]. In Proceedings of WI’06,2006:572-580.
[96] Zhang S and Liu J. A Massively Multi-agent System for DiscoveringHIV-immune Interaction Dynamics [C]. In Proceedings of MMAS’04,2004:161-173.
[97] Liu J and Hu B. On Emergent Complex Behaviour, Selforganised Criticalityand Phase Transitions in Multi-agent Systems: Autonomy Oriented Computing(AOC) Perspectives [J]. International Journal of Modelling, Identification andControl,3(1),2008:3-16.
[98] Jin X and Liu J. From Individual Based Modeling to Autonomy OrientedComputation [J]. LNAI2969,2004:151-169.
[99] Liu J, Jing H, and Tang Y Y. Multi-agent Oriented Constraint Satisfaction [J].Artificial Intelligence,136(1),2002:101-144.
[100]Tsui K C and Liu J. Multiagent Diffusion and Distributed Optimization [C]. InProceedings of AAMAS’03,2003:169-176.
[101]Xie X F and Liu J. How Autonomy Oriented Computing (AOC) Tackles aComputationally Hard Optimization Problem [C]. In Proceedings ofAAMAS’06,2006:646-653.
[102]Kaiser M J, Tsui K C, and Liu J. Self-organized Autonomous Web Proxies [C].In Proceedings of AAMAS’02,2002:1397-1404.
[103]Gan L, Liu J, and Jin X. Agent-based, Energy Efficient Routing in SensorNetworks [C]. In Proceedings of AAMAS’04,2004:472-479.
[104]Yang B and Liu J. An Autonomy Oriented Computing (AOC) Approach toDistributed Network Community Mining [C]. In Proceedings of SASO’07,2007:151-160.
[105]Yang B and Liu J. Discovering Global Network Communities Based on LocalCentralities [J]. ACM Transactions on the Web,2(1),2008:1-32.
[106]Liu J and Wu J. Multiagent Robotic Systems [M]. CRC Press,2001.
[107]Liu J, Jin X and Wang Y. Agent-based Load Balancing on HomogeneousMinigrids: Macroscopic Modeling and Characterization [J]. IEEE Transactionson Parallel and Distributed Systems,16(7),2005:586-598.
[108]Mirroshandel S A and Nasr A. Active Learning for Dependency Parsing UsingPartially Annotated Sentences [C]. In Proceedings of IWPT,2011:140-149.
[109]Jiang W and Liu Q. Dependency Parsing and Projection Based on Word-pairClassification [C]. In Proceedings of the48th Annual Meeting of theAssociation for Computational Linguistics (ACL '10). Association forComputational Linguistics, Stroudsburg, PA, USA,2010:12-20.
[110]Chen W, Kazama J, and Zhang M. SMT Helps Bitext Dependency Parsing [C].In Proceedings of the Conference on Empirical Methods in Natural LanguageProcessing (EMNLP '11). Association for Computational Linguistics,2011:73-83.
[111]Gadde P, Jindal K, Husain S, et al. Improving Data Driven DependencyParsing Using Clausal Information [C]. In Human Language Technologies: The2010Annual Conference of the North American Chapter of the Association forComputational Linguistics (HLT '10),2010:657-660.
[112]Agirre E, Bengoetxea K, Gojenola K, et al. Improving Dependency ParsingWith Semantic Classes [C]. In Proceedings of the49th Annual Meeting of theAssociation for Computational Linguistics: Human Language Technologies:short papers,2011:699-703.
[113]Marton Y, Habash N, and Rambow O. Improving Arabic Dependency ParsingWith Form-based and Functional Morphological Features [C]. In Proceedingsof the49th Annual Meeting of the Association for Computational Linguistics:Human Language Technologies,2011:1586-1596.
[114]Zhou G, Zhao J, Liu K, et al. Exploiting Web-derived Selectional Preference toImprove Statistical Dependency Parsing [C]. In Proceedings of the49thAnnual Meeting of the Association for Computational Linguistics: HumanLanguage Technologies,2011:1556-1565.
[115]Bergsma S and Cherry C. Fast and Accurate Arc Filtering for DependencyParsing [C]. In Proceedings of the23rd International Conference onComputational Linguistics (COLING '10),2010:53-61.
[116]McDonald R, Crammer K, and Pereira F. Online Large-margin Training ofDependency Parsers [C]. In Proceedings of the43rd Annual Meeting onAssociation for Computational Linguistics (ACL '05),2005:91-98.
[117]McDonald R and Pereira F. Online Learning of Approximate DependencyParsing Algorithms [C]. Proceedings of11th Conference of the EuropeanChapter of the Association for Computational Linguistics (EACL-2006),2006:81-88.
[118]Wu Y, Zhang Q, Huang X, et al. Structural Opinion Mining for Graph-basedSentiment Representation [C]. In Proceedings of the Conference on EmpiricalMethods in Natural Language Processing (EMNLP '11),2011:1332-1341.
[119]McClosky D, Surdeanu M, and Manning C D. Event Extraction as DependencyParsing [C]. In Proceedings of the49th Annual Meeting of the Association forComputational Linguistics: Human Language Technologies,2011:1626-1635.
[120]Xu J and Li H. AdaRank: A Boosting Algorithm for Information Retrieval [C].In Proceedings of the30th annual international ACM SIGIR conference onResearch and development in information retrieval,2007:391-398.
[121]Nallapati R. Discriminative Models for Information Retrieval [C]. InProceedings of the27th annual international ACM SIGIR conference onResearch and development in information retrieval,2004:64-71.
[122]Li P, Burges C, and Wu Q. McRank: Learning to Rank Using Classificationand Gradient Boosting [C]. In Proceedings of the International Conference onAdvances in Neural Information Processing Systems,2007.
[123]Caruana R, Baluja S, and Mitchell T. Using the Future to “sort out” the Present:Rankprop and Multitask Learning for Medical Risk Evaluation [C]. InProceedings of the International Conference on Advances in NeuralInformation Processing Systems,1996:959-965.
[124]Joachims T. Optimizing Search Engine using Clickthrough Data [C]. InProceedings of the ACM Conference on Knowledge, Discovery and DataMining,2002:133-142.
[125]Burges C, Ragno R, and Le Q V L. Learning to Rank With Non Smooth CostFunctions [C]. In Proceedings of the International Conference on Advances inNeural Information Processing Systems,2006:193-200.
[126]Burges C, Shaked T, Renshaw E, et al. Learning to Rank Using GradientDescent [C]. In Proceedings of the22nd International Conference on MachineLearning, Bonn, Germany,2005:89-96.
[127]Freund Y and Schapire R E. Experiments With A New Boosting Algorithm [C].In Proceedings of the13th International Conference on Machine Learning,1996:148-156.
[128]Qin T, Liu T Y, Tsai, M F, et al. Learning to Search Web Pages WithQuery-level Loss Functions [R]. Technical Report MSR-TR-2006-156,2006.
[129]Cao Z, Qin T, Liu T, et al. Learning to Rank: From Pairwise Approach toListwise Approach [C]. In Proceedings of the24th international conference onMachine learning,2007:129-136.
[130]Chaudhuri S, Ganjam K, Ganti V, et al. Robust And Efficient Fuzzy Match forOnline Data Cleaning [C]. In Proceedings of the2003ACM SIGMODinternational conference on Management of data,2003:313-324.
[131]Arasu A, Ganti V, and Kaushik R. Efficient Exact Set-similarity Joins [C]. InProceedings of the32nd international conference on Very large data bases,2006:918-929.
[132]Chandel A, Hassanzadeh O, Koudas N, et al. Benchmarking DeclarativeApproximate Selection Predicates [C]. In Proceedings of the2007ACMSIGMOD international conference on Management of data,2007:353-364.
[133]Cormen T H, Lerserson C E, Rivest R L, et al. Introduction of Algorithms [M].Second Edition. China Machine Press,2006:396-419.
[134]Su F and Markert K. Subjectivity Recognition on Word Senses viaSemi-supervised Mincuts [C]. Human Language Technologies: The2009Annual Conference of the North American Chapter of the ACL,2009:1-9.
[135]许洪波,孙乐,姚天昉.第三届中文倾向性分析评测总结报告[C].第三届中文倾向性分析评测(The Third Chinese Opinion Analysis Evaluation2011,COAE2011),2011:1-24.
[136]Xu R, Wang Y, Xu J, et al. Chinese Opinion Analysis based on MultiKnowledge Integration and Multi Classifier Voting [C]. In COAE2011,2011:77-87.
[137]Pelletier N, McHeyzer-Williams L J, Kurt A W, et al. Plasma Cells NegativelyRegulate the Follicular Helper T cell Program [J]. Nature Immunology,11(12),2010:1110-1118.
[138]Joel L S. Cellular Automaton: A Discrete View of the World [J].WileyInterscience,2007:39-184.
[139]Xue N, Xia F, Chiou F, et al. The Penn Chinese Treebank: Phrase StructureAnnotation of a Large Corpus [J]. Natural Language Engineering,11(2),2005:207-238.
[140]Zhang Y and Clark S. A Tale of Two Parsers: Investigating and CombiningGraph-based and Transition-based Dependency Parsing [C]. In Proceedings ofEMNLP2008,2008:562-571.
[141]Li Z, Zhang M, Che W, et al. Joint Models for Chinese POS Tagging andDependency Parsing [C]. In Proceedings of the Conference on EmpiricalMethods in Natural Language Processing,2011:1180-1191.
[142]Kobayashi N, Inui K, Matsumoto Y. Collecting Evaluative Expressions forOpinion Extraction [C]. In Proceedings of the International Joint Conferenceon Natural Language Processing (IJCNLP).2004.
[143]王中卿,王荣洋,庞磊等. Suda_SAM_OMS情感倾向性分析技术报告[C].第三届中文倾向性分析评测(The Third Chinese Opinion Analysis Evaluation2011, COAE2011),2011:25-32.
[144]Bloom K, Garg N, Argamon S. Extracting Appraisal Expressions [C]. In:Proceedings of HLT-NAACL2007.2007.308-315.
[145]姚天昉,聂青阳,李建超等.一个用于汉语汽车评论的意见挖掘系统[C].中国中文信息学会成立二十五周年学术年会论文集.2006:260-281.
[146]赵妍妍,秦冰,刘挺.文本情感分析[J].软件学报,21(8),2010:1834-1848
[2] Horrigan J. Online shopping [R]. Pew Internet&American Life Project Report,2008.
[3] Zabin J and Jefferies A. Social Media Monitoring and Analysis: GeneratingConsumer Insights from Online Conversation [R]. Aberdeen Group BenchmarkReport,2008.
[4] Taboada M, Brooke J, Tofiloski M, et al. Lexicon-Based Methods forSentiment Analysis [J]. Computational Linguistics,37(2),2011:267-307.
[5] Tetsuya N and Yi J. Sentiment Analysis: Capturing Favorability Using NaturalLanguage Processing [C]. In Proceedings of the KCAP-03,2nd Intl. Conf. onKnowledge Capture,2003:70-77.
[6] Terveen L, Hill W, Amento B, et al. PHOAKS: A System for SharingRecommendations. Communications of the Association for ComputingMachinery (CACM),40(3),1997:59-62.
[7] Lita L, Schlaikjer A, Hong W, and Nyberg E. Qualitative Dimensions inQuestion Answering: Extending the Definitional QA task [C]. In Proceedingsof AAAI,2005:1616-1617.
[8] Somasundaran S, Wilson T, Wiebe J, et al. QA with Attitude: ExploitingOpinion Type Analysis for Improving Question Answering in On-lineDiscussions and the News [C]. In Proceedings of the International Conferenceon Weblogs and Social Media (ICWSM),2007.
[9] Stoyanov V, Cardie C, and Wiebe J. Multi-perspective Question AnsweringUsing the OpQA Corpus [C]. In Proceedings of the Human LanguageTechnology Conference and the Conference on Empirical Methods in NaturalLanguage Processing (HLT/EMNLP),2005:923-930.
[10] Seki Y, Eguchi Y, Kando N, et al. Multi-document Summarization withSubjectivity Analysis at DUC2005[C]. In Proceedings of the DocumentUnderstanding Conference (DUC),2005.
[11] Abbasi A. Affect Intensity Analysis of Dark Web Forums [C]. In Proceedingsof Intelligence and Security Informatics (ISI),2007:282-288.
[12] Yu, X., Liu, Y., Huang, X., An, A. Mining Online Reviews for Predicting SalesPerformance: A Case Study in the Movie Domain [J]. IEEE Trans. Knowl.Data Eng.2012:720-734.
[13] Pang B, Lee L, and Vaithyanathan S. Thumbs up? Sentiment Classificationusing Machine Learning Techniques [C]. In Proceedings of Empirical Methodson Natural Language Processing,2002:79-86.
[14] Pang B and Lee L. A Sentimental Education: Sentiment Analysis UsingSubjectivity Summarization Based on Minimum Cuts [C]. In Proceedings ofthe42nd Annual Meeting on Association for Computational Linguistics,2004:271-278.
[15]许洪波,姚天昉,黄萱菁.第二届中文倾向性分析评测技术报告[C].第二届中文倾向性分析评测(The Second Chinese Opinion Analysis Evaluation2009, COAE2009),2009:1-23.
[16] Pang B and Lee L. Opinion Mining and Sentiment Analysis [J]. Foundationsand Trends in Information Retrieval,2(1-2),2008:1-135.
[17] Kim S and Hovy E. Determining the Sentiment of Opinions [C]. InProceedings of COLING,2004:1367-1373.
[18] Mao Y and Lebanon G. Isotonic Conditional Random Fields and LocalSentiment Flow [C]. In Proceedings of NIPS,2006:961-968.
[19] Abbasi A, France S, Zhang Z, et al. Selecting Attributes for SentimentClassification Using Feature Relation Networks [J]. IEEE Transactions onKnowledge and Data Engineering,23(3),2011:447-462.
[20] Tan C, Lee L, Tang J, et al. User-level Sentiment Analysis Incorporating SocialNetworks [C]. In Proceedings of the17th ACM SIGKDD InternationalConference on Knowledge Discovery and Data Mining,2011:1397-1405.
[21] Mohtarami M, Amiri H, Lan M, et al. Predicting the Uncertainty of SentimentAdjectives in Indirect Answers [C]. In Proceedings of the20th ACMInternational Conference on Information and Knowledge Management,2011:2485-2488.
[22] Qin B, Zhao Y, Gao L, et al. Recommended or Not? Give advice on OnlineProduct [C]. Fifth international conference on Fuzzy Systems and KnowledgeDiscovery,2008:208-212.
[23] Thelwall M, Buckley K, and Paltoglou G. Sentiment in Twitter Events [J].Journal of the American Society for Information Science and Technology,62(2),2011:406-418.
[24]王中卿,李寿山,朱巧明等.基于不平衡数据的中文情感分类[J].中文信息学报,26（3），2012:33-37.
[25] Yan L and Zhang Y. News Sentiment Analysis Based on Cross-DomainSentiment Word Lists and Content Classifiers [C]. Advanced Data Mining andApplications, Lecture Notes in Computer Science Volume7713,2012:577-588.
[26] Glorot X, Bordes A, and Bengio Y. Domain Adaptation for Large-ScaleSentiment Classification: A Deep Learning Approach [C]. In Proceedings ofthe Twenty-eight International Conference on Machine Learning,2011:513-520.
[27] Jerne N. THE GENERATIVE GRAMMAR OF THE IMMUNE SYSTEM [R].Nobel lecture,8December,1984.
[28]宋晓雷,王素格,李红霞等.基于概率潜在语义分析的词汇情感倾向判别[J].中文信息学报,25(2),2011:89-93.
[29] Wu Y and Wen M. Disambiguating Dynamic Sentiment Ambiguous Adjectives
[C]. Proceeding COLING '10Proceedings of the23rd International Conferenceon Computational Linguistics,2010:1191-1199.
[30] Hassan A and Radev D. Identifying Text Polarity Using Random Walks [C].Proceeding ACL '10Proceedings of the48th Annual Meeting of theAssociation for Computational Linguistics,2010:395-403.
[31] Das D and Bandyopadhyay S. Word to Sentence Level Emotion Tagging forBengali Blogs [C]. Proceeding ACL Short '09Proceedings of the ACL-IJCNLP2009Conference Short Papers,2009:149-152.
[32] Rao D and Ravichandran D. Semi-Supervised Polarity Lexicon Induction [C].Proceedings of the12th Conference of the European Chapter of the ACL,2009:675-682.
[33] Blum A, Lafferty J, Rwebangira M R, et al. Semi-supervised Learning UsingRandomized Mincuts [C]. In Proceedings of the ICML,2004.
[34] Zhu X and Ghahramani Z. Learning from Labeled and Unlabeled Data withLabel Propagation [R]. Technical Report CMU-CALD-02-107, CarnegieMellon University.2002.
[35] Fu G and Wang X. Chinese Sentence-level Sentiment Classification based onFuzzy Sets [C]. Proceeding COLING '10Proceedings of the23rd InternationalConference on Computational Linguistics,2010:312-319.
[36] Meena A and Prabhakar T V. Sentence Level Sentiment Analysis in thePresence of Conjuncts Using Linguistic Analysis [J]. Advances in InformationRetrieval, vol.4425. Berlin, Heidelberg: Springer Berlin Heidelberg,2007:573-580.
[37] Xia R and Zong C. Exploring the Use of Word Relation Features for SentimentClassification [C]. Proceeding COLING '10Proceedings of the23rdInternational Conference on Computational Linguistics,2010:1336-1344.
[38] Davidov D, Tsur O, and Rappoport A. Enhanced Sentiment Learning UsingTwitter Hashtags and Smileys [C]. Proceedings of the23rd InternationalConference on Computational Linguistics,2010:241-249.
[39] Wei W and Gulla J A. Sentiment Learning on Product Reviews via SentimentOntology Tree [C]. Proceeding ACL '10Proceedings of the48th AnnualMeeting of the Association for Computational Linguistics,2010:404-413.
[40] Jang H and Shin H. Language-specific Sentiment Analysis in MorphologicallyRich Languages [C]. Proceeding COLING '10Proceedings of the23rdInternational Conference on Computational Linguistics, Aug,2010:498-506.
[41] Zhang Q, Wu Y, Li T, et al. Mining Product Reviews based on ShallowDependency Parsing [C]. In Proceedings of the32nd international ACM SIGIRconference on Research and development in information retrieval,2009:726-727.
[42]王根,赵军.基于多重标记CRF句子情感分析的研究[C].全国第九届计算机语言学学术会议.2007.
[43] Guo H, Zhu H, Guo Z, et al. Domain Customization for Aspect-orientedOpinion Analysis with Multi-level Latent Sentiment Clues [C]. In Proceedingsof the20th ACM International Conference on Information and KnowledgeManagement,2011:2493-2496.
[44] Wei B and Pal C. Cross Lingual Adaptation: An Experiment on SentimentClassifications [C]. Proceeding ACL Short’10Proceedings of the ACL2010Conference Short Papers,2010:258–262.
[45] Socher R, Pennington J, Huang E H, et al. Semi-supervised RecursiveAuto-encoders for Predicting Sentiment Distributions [C]. Proceedings of the2011Conference on Empirical Methods in Natural Language Processing,2011:151-161.
[46] Taboada M, Brooke J, Tofiloski M, et al. Lexicon-Based Methods forSentiment Analysis [J]. Computational Linguistics,37(20),2011:267-307.
[47] Andrew L. M, Raymond E. D, Peter T. P, et al. Learning Word Vectors forSentiment Analysis [C]. In Proceedings of the49th Annual Meeting of theAssociation for Computational Linguistics: Human Language Technologies,2011:142-150.
[48] Tan S and Wang Y. Weighted SCL Model for Adaptation of SentimentClassification [J]. Expert Systems with Applications,38(8),2011:10524-10531.
[49] Wu Q, Tan S, Cheng X, et al. MIEA: a Mutual Iterative EnhancementApproach for Cross-Domain Sentiment Classification [C]. Coling2010Posters,2010:1327-1335.
[50] Agarwal A, Xie B, Vovsha I, et al. Sentiment Analysis of Twitter Data [C].Proceeding LSM '11Proceedings of the Workshop on Languages in SocialMedia, Jun,2011:30-38.
[51] Balamurali A, Joshi A, and Bhattacharyya P. Harnessing WordNet Senses forSupervised Sentiment Classification [C]. EMNLPACL,2011:1081-1091.
[52] Li S, Lee S Y M, Chen Y, et al. Sentiment Classification and Polarity Shifting
[C]. Proceeding COLING '10Proceedings of the23rd International Conferenceon Computational Linguistics, Aug,2010:635-643.
[53] Paltoglou G and Thelwall M. A Study of Information Retrieval WeightingSchemes for Sentiment Analysis [C]. Proceeding ACL '10Proceedings of the48th Annual Meeting of the Association for Computational Linguistics, Jul,2010:1386-1395.
[54] Li S, Xia R, Zong C, and Huang C. A Framework of Feature Selection Methodsfor Text Categorization [C]. Proceeding ACL '09Proceedings of the JointConference of the47th Annual Meeting of the ACL and the4th InternationalJoint Conference on Natural Language Processing of the AFNLP,2009:692-700.
[55] Abbasi A, Chen H, and Salem A. Sentiment Analysis in Multiple Languages [J].ACM Transactions on Information Systems,26(3),2008:1-34.
[56] McDonald R, Hannan K, Neylon T, et al. Structured Models for Fine-to-CoarseSentiment Analysis [C]. Proceedings of the Association for ComputationalLinguistics,2007:432-439.
[57]徐琳宏,林鸿飞,杨志豪.基于语义理解的文本倾向性识别机制[J].中文信息学报,21(1),2007:96-100
[58] Wang S, Wei Y, Li D, et al. A Hybrid Method of Feature Selection for ChineseText Sentiment Classification [C]. In Fourth International Conference onFuzzy Systems and Knowledge Discovery,2007:435-439.
[59] Wan X. Bilingual Co-Training for Sentiment Classification of Chinese ProductReviews [J]. Computational Linguistics,37(3),2011:587-616.
[60] Tan C, Lee L, Tang J, et al. User-level Sentiment Analysis Incorporating SocialNetworks [C]. In Proceedings of the17th ACM SIGKDD internationalconference on Knowledge discovery and data mining,2011:1397-1405.
[61] Forrest S, Perelson A, Allen L, et al. Self-nonself Discrimination in aComputer [C]. In Proceedings of the1994IEEE Symposium on Research inSecurity and Privacy,1994:202-212.
[62] Dasgupta D and Forrest S. An Anomaly Detection Algorithm Inspired by theImmune System [J]. Artificial Immune System and Their Applications,57,1999:262-277.
[63] Dasgupta D, Yu S, and Nino F. Recent Advances in Artificial Immune Systems:Models and Applications [J]. Applied Soft Computing,11(2),2011:1574-1587.
[64] Luo W, Wang J, and Wang X. Evolutionary Negative Selection Algorithms forAnomaly Detection [C], In8th Joint Conference on Information Science(JCIS2005),2005.
[65] Luo W, Guo P, and Wang X. On Convergence of Evolutionary NegativeSelection Algorithms for Anomaly Detection [C]. In IEEE Congress onEvolutionary Computation (CEC)(IEEE World Congress on ComputationalIntelligence),2008:2933-2939.
[66] Xu B, Luo W, Pei X, et al. On Average Time Complexity of EvolutionaryNegative Selection Algorithms for Anomaly Detection [C]. In2009WorldSummit on Genetic and Evolutionary Computation (2009GEC Summit),2009.
[67] Zhanga Y, Luo W, Zhang Z, et al. A Hardware/Software Partitioning Algorithmbased on Artificial Immune Principles [J]. Applied Soft Computing,2008:383-391.
[68] Dasgupta D, KrishnaKumar K, Wong D, et al. Negative Selection Algorithmfor Aircraft Fault Detection [C]. In G. Nicosia et al.(Eds), Proceedings ofThird International Conference on Artificial Immune Systems (ICARIS2004),2004:1-13.
[69] Gan Z, Zhao M B, and Chow T W S. Induction Machine Fault Detection UsingClone Selection Programming [J]. Expert System with Applications,34(4),2009:8000-8012.
[70] Dasgupta D and Gonzalez F. An Immunity-based Technique to CharacterizeIntrusions in Computer Networks [J]. IEEE Transactions on EvolutionaryComputation,6(3),2002:281-291.
[71] Jerne N K. Towards a network theory of the immune system [J]. Annalesd’immunologie,125C (1-2),1974:373–389.
[72] Ishida Y. Fully distributed diagnosis by PDP learning algorithm: towardsimmune network PDP model [C]. IEEE International Joint Conference onNeural Networks,1990.
[73] Farmer J D, Packard N H, and Perelson A S. The immune system, adaptation,and machine learning [J]. Physica D: Nonlinear Phenomena,22(1-3),1986:187-204.
[74] Ou C M and Ou C R. Immune Network and Immune Memory Mechanism:Perspectives on Dynamical Systems [C]. In2011International Conference onTechnologies and Applications of Artificial Intelligence,2011:313-318.
[75] Madi A, Kenett D Y, Bransburg-Zabary S, et al. Network Theory Analysis ofAntibody-Antigen Reactivity Data: The Immune Trees at Birth and Adulthood[J]. PLoS ONE,6(3),2011:1-11.
[76] Souza-e-Silva H and dos Santos R M Z. Is the Immune Network a ComplexNetwork? arXiv.org,2012:1-10.
[77] Coelho G, Von Zuben F, Takahashi R, et al. A Concentration-Based ArtificialImmune Network for Multi-objective Optimization [J]. EvolutionaryMulti-Criterion Optimization,6576,2011:343-357.
[78] Gong M, Jiao L, Yang J, and Liu F. Lamarckian Learning in Clonal SelectionAlgorithm for Numerical Optimization [J]. International Journal on ArtificialIntelligence Tools,19(1),2010:19-37.
[79] Gong M, Jiao L, and Zhang L. Baldwinian Learning in Clonal SelectionAlgorithm for Optimization [J]. Information Sciences,180(8),2010:1218-1236.
[80] Tiwari M K, Prakash Kumar A, and Mileham AR. Determination of an OptimalAssembly Sequence Using the PsychoCA [J]. Journal of EngineeringManufacture,2005:137-149
[81] Maier N R F. Psychology in Industry [M].3rd edition,1965:417-419.
[82] Liu X, Shi L, Chen R, and Chen H. A Novel Clonal Selection Algorithm forGlobal Optimization Problems [C]. In International conference on informationengineering and computer science,2009:1-4.
[83] Yang J, Sun L, Lee H P, et al. Clonal Selection based Memetic Algorithm forJob Shop Scheduling Problems [J]. Journal of Bionic Engineering,5(2),2008:111-119.
[84] Garain U, Chakraborty M P, and Dasgupta D. Recognition of HandwrittenIndict Script Using Clonal Selection Algorithm [C]. In Proceedings of the5thinternational conference on Artificial Immune Systems (ICARIS'06),2006:256-266.
[85] Moghaddam M Z and Kardan A. Clonal Selection Algorithm for Partitioningand Scheduling of Codesign Systems [C]. In5th International colloquium onsignal processing and its applications,2009:267-272.
[86] Dai H and Li C. Chaotic Immune Clonal Selection Algorithm and itsApplication [C]. In Proceedings of the2nd international symposium onknowledge acquisition and modeling (KAM2009),2009:65-68.
[87] Gao X Z, Wang X, and Ovaska S J. Fusion of Clonal Selection Algorithm andDifferential Evolution Method in Training Cascade-correlation NeuralNetwork [J]. Neurocomputing,72(10-12),2009:2483-2490.
[88] Li D and Chen Z. SVM Optimized by Immune Clonal Selection Algorithm forFault Diagnostics [C]. In Proceedings Pacific-Asia conference on circuits,communications and systems (PACCS2009),2009:702-705.
[89] Yong L and Sunjun L. A Hybrid Model for Solving TSP based on ArtificialImmune and Ant Colony [C]. In International conference on informationengineering and computer science (ICIECS2009),2009:605-609.
[90] Rocha L M. Complex Systems Modeling: Using Metaphors From Nature inSimulation and Scientific Models. BITS: Computer and CommunicationsNews [R]. Computing, Information, and Communications Division. LosAlamos National Laboratory.1999.
[91] Wolfram S. Cellular Automata as Models of Complexity [J]. Nature,311,1984:419-424.
[92] Liu J, Jin X, and Tsui K C. Autonomy-Oriented Computing (AOC):Formulating Computational Systems With Autonomous Components [J]. IEEETRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS-PART A:SYSTEMS AND HUMANS,35(6),2005:879-902.
[93] Liu J. Autonomy-Oriented Computing (AOC): Formulating ComputationalSystems With Autonomous Components [C]. In Proceedings of the fourthinternational conference on natural computation (Keynote talk),2008:3-11.
[94] Liu J, Zhang S, and Yang J. Characterizing Web Usage Regularities withInformation Foraging Agents [J]. IEEE Transactions on Knowledge and DataEngineering,16(5),2004:566-584.
[95] Zhang S and Liu J. From Local Behaviors to the Dynamics in an AgentNetwork [C]. In Proceedings of WI’06,2006:572-580.
[96] Zhang S and Liu J. A Massively Multi-agent System for DiscoveringHIV-immune Interaction Dynamics [C]. In Proceedings of MMAS’04,2004:161-173.
[97] Liu J and Hu B. On Emergent Complex Behaviour, Selforganised Criticalityand Phase Transitions in Multi-agent Systems: Autonomy Oriented Computing(AOC) Perspectives [J]. International Journal of Modelling, Identification andControl,3(1),2008:3-16.
[98] Jin X and Liu J. From Individual Based Modeling to Autonomy OrientedComputation [J]. LNAI2969,2004:151-169.
[99] Liu J, Jing H, and Tang Y Y. Multi-agent Oriented Constraint Satisfaction [J].Artificial Intelligence,136(1),2002:101-144.
[100]Tsui K C and Liu J. Multiagent Diffusion and Distributed Optimization [C]. InProceedings of AAMAS’03,2003:169-176.
[101]Xie X F and Liu J. How Autonomy Oriented Computing (AOC) Tackles aComputationally Hard Optimization Problem [C]. In Proceedings ofAAMAS’06,2006:646-653.
[102]Kaiser M J, Tsui K C, and Liu J. Self-organized Autonomous Web Proxies [C].In Proceedings of AAMAS’02,2002:1397-1404.
[103]Gan L, Liu J, and Jin X. Agent-based, Energy Efficient Routing in SensorNetworks [C]. In Proceedings of AAMAS’04,2004:472-479.
[104]Yang B and Liu J. An Autonomy Oriented Computing (AOC) Approach toDistributed Network Community Mining [C]. In Proceedings of SASO’07,2007:151-160.
[105]Yang B and Liu J. Discovering Global Network Communities Based on LocalCentralities [J]. ACM Transactions on the Web,2(1),2008:1-32.
[106]Liu J and Wu J. Multiagent Robotic Systems [M]. CRC Press,2001.
[107]Liu J, Jin X and Wang Y. Agent-based Load Balancing on HomogeneousMinigrids: Macroscopic Modeling and Characterization [J]. IEEE Transactionson Parallel and Distributed Systems,16(7),2005:586-598.
[108]Mirroshandel S A and Nasr A. Active Learning for Dependency Parsing UsingPartially Annotated Sentences [C]. In Proceedings of IWPT,2011:140-149.
[109]Jiang W and Liu Q. Dependency Parsing and Projection Based on Word-pairClassification [C]. In Proceedings of the48th Annual Meeting of theAssociation for Computational Linguistics (ACL '10). Association forComputational Linguistics, Stroudsburg, PA, USA,2010:12-20.
[110]Chen W, Kazama J, and Zhang M. SMT Helps Bitext Dependency Parsing [C].In Proceedings of the Conference on Empirical Methods in Natural LanguageProcessing (EMNLP '11). Association for Computational Linguistics,2011:73-83.
[111]Gadde P, Jindal K, Husain S, et al. Improving Data Driven DependencyParsing Using Clausal Information [C]. In Human Language Technologies: The2010Annual Conference of the North American Chapter of the Association forComputational Linguistics (HLT '10),2010:657-660.
[112]Agirre E, Bengoetxea K, Gojenola K, et al. Improving Dependency ParsingWith Semantic Classes [C]. In Proceedings of the49th Annual Meeting of theAssociation for Computational Linguistics: Human Language Technologies:short papers,2011:699-703.
[113]Marton Y, Habash N, and Rambow O. Improving Arabic Dependency ParsingWith Form-based and Functional Morphological Features [C]. In Proceedingsof the49th Annual Meeting of the Association for Computational Linguistics:Human Language Technologies,2011:1586-1596.
[114]Zhou G, Zhao J, Liu K, et al. Exploiting Web-derived Selectional Preference toImprove Statistical Dependency Parsing [C]. In Proceedings of the49thAnnual Meeting of the Association for Computational Linguistics: HumanLanguage Technologies,2011:1556-1565.
[115]Bergsma S and Cherry C. Fast and Accurate Arc Filtering for DependencyParsing [C]. In Proceedings of the23rd International Conference onComputational Linguistics (COLING '10),2010:53-61.
[116]McDonald R, Crammer K, and Pereira F. Online Large-margin Training ofDependency Parsers [C]. In Proceedings of the43rd Annual Meeting onAssociation for Computational Linguistics (ACL '05),2005:91-98.
[117]McDonald R and Pereira F. Online Learning of Approximate DependencyParsing Algorithms [C]. Proceedings of11th Conference of the EuropeanChapter of the Association for Computational Linguistics (EACL-2006),2006:81-88.
[118]Wu Y, Zhang Q, Huang X, et al. Structural Opinion Mining for Graph-basedSentiment Representation [C]. In Proceedings of the Conference on EmpiricalMethods in Natural Language Processing (EMNLP '11),2011:1332-1341.
[119]McClosky D, Surdeanu M, and Manning C D. Event Extraction as DependencyParsing [C]. In Proceedings of the49th Annual Meeting of the Association forComputational Linguistics: Human Language Technologies,2011:1626-1635.
[120]Xu J and Li H. AdaRank: A Boosting Algorithm for Information Retrieval [C].In Proceedings of the30th annual international ACM SIGIR conference onResearch and development in information retrieval,2007:391-398.
[121]Nallapati R. Discriminative Models for Information Retrieval [C]. InProceedings of the27th annual international ACM SIGIR conference onResearch and development in information retrieval,2004:64-71.
[122]Li P, Burges C, and Wu Q. McRank: Learning to Rank Using Classificationand Gradient Boosting [C]. In Proceedings of the International Conference onAdvances in Neural Information Processing Systems,2007.
[123]Caruana R, Baluja S, and Mitchell T. Using the Future to “sort out” the Present:Rankprop and Multitask Learning for Medical Risk Evaluation [C]. InProceedings of the International Conference on Advances in NeuralInformation Processing Systems,1996:959-965.
[124]Joachims T. Optimizing Search Engine using Clickthrough Data [C]. InProceedings of the ACM Conference on Knowledge, Discovery and DataMining,2002:133-142.
[125]Burges C, Ragno R, and Le Q V L. Learning to Rank With Non Smooth CostFunctions [C]. In Proceedings of the International Conference on Advances inNeural Information Processing Systems,2006:193-200.
[126]Burges C, Shaked T, Renshaw E, et al. Learning to Rank Using GradientDescent [C]. In Proceedings of the22nd International Conference on MachineLearning, Bonn, Germany,2005:89-96.
[127]Freund Y and Schapire R E. Experiments With A New Boosting Algorithm [C].In Proceedings of the13th International Conference on Machine Learning,1996:148-156.
[128]Qin T, Liu T Y, Tsai, M F, et al. Learning to Search Web Pages WithQuery-level Loss Functions [R]. Technical Report MSR-TR-2006-156,2006.
[129]Cao Z, Qin T, Liu T, et al. Learning to Rank: From Pairwise Approach toListwise Approach [C]. In Proceedings of the24th international conference onMachine learning,2007:129-136.
[130]Chaudhuri S, Ganjam K, Ganti V, et al. Robust And Efficient Fuzzy Match forOnline Data Cleaning [C]. In Proceedings of the2003ACM SIGMODinternational conference on Management of data,2003:313-324.
[131]Arasu A, Ganti V, and Kaushik R. Efficient Exact Set-similarity Joins [C]. InProceedings of the32nd international conference on Very large data bases,2006:918-929.
[132]Chandel A, Hassanzadeh O, Koudas N, et al. Benchmarking DeclarativeApproximate Selection Predicates [C]. In Proceedings of the2007ACMSIGMOD international conference on Management of data,2007:353-364.
[133]Cormen T H, Lerserson C E, Rivest R L, et al. Introduction of Algorithms [M].Second Edition. China Machine Press,2006:396-419.
[134]Su F and Markert K. Subjectivity Recognition on Word Senses viaSemi-supervised Mincuts [C]. Human Language Technologies: The2009Annual Conference of the North American Chapter of the ACL,2009:1-9.
[135]许洪波,孙乐,姚天昉.第三届中文倾向性分析评测总结报告[C].第三届中文倾向性分析评测(The Third Chinese Opinion Analysis Evaluation2011,COAE2011),2011:1-24.
[136]Xu R, Wang Y, Xu J, et al. Chinese Opinion Analysis based on MultiKnowledge Integration and Multi Classifier Voting [C]. In COAE2011,2011:77-87.
[137]Pelletier N, McHeyzer-Williams L J, Kurt A W, et al. Plasma Cells NegativelyRegulate the Follicular Helper T cell Program [J]. Nature Immunology,11(12),2010:1110-1118.
[138]Joel L S. Cellular Automaton: A Discrete View of the World [J].WileyInterscience,2007:39-184.
[139]Xue N, Xia F, Chiou F, et al. The Penn Chinese Treebank: Phrase StructureAnnotation of a Large Corpus [J]. Natural Language Engineering,11(2),2005:207-238.
[140]Zhang Y and Clark S. A Tale of Two Parsers: Investigating and CombiningGraph-based and Transition-based Dependency Parsing [C]. In Proceedings ofEMNLP2008,2008:562-571.
[141]Li Z, Zhang M, Che W, et al. Joint Models for Chinese POS Tagging andDependency Parsing [C]. In Proceedings of the Conference on EmpiricalMethods in Natural Language Processing,2011:1180-1191.
[142]Kobayashi N, Inui K, Matsumoto Y. Collecting Evaluative Expressions forOpinion Extraction [C]. In Proceedings of the International Joint Conferenceon Natural Language Processing (IJCNLP).2004.
[143]王中卿,王荣洋,庞磊等. Suda_SAM_OMS情感倾向性分析技术报告[C].第三届中文倾向性分析评测(The Third Chinese Opinion Analysis Evaluation2011, COAE2011),2011:25-32.
[144]Bloom K, Garg N, Argamon S. Extracting Appraisal Expressions [C]. In:Proceedings of HLT-NAACL2007.2007.308-315.
[145]姚天昉,聂青阳,李建超等.一个用于汉语汽车评论的意见挖掘系统[C].中国中文信息学会成立二十五周年学术年会论文集.2006:260-281.
[146]赵妍妍,秦冰,刘挺.文本情感分析[J].软件学报,21(8),2010:1834-1848
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |