基于动量模型的食品安全事件发现方法
|
摘要
食品安全是广受民众关注的热点话题,而微博已经成为食品安全事件曝光的主要媒体平台.以微博语料作为数据源,同时使用微博内容和用户的社交网络行为特征,提出了基于动量模型的食品安全事件发现方法.该方法以事件发现作为描述食品安全事件的基本模型,以检测出微博信息流中与食品安全相关的候选特征词,然后采用动量模型实现候选特征词的动量建模和重复特征词的有效过滤.最后,通过K-means聚类将有效的特征词进行归类合并,以实现食品安全事件的发现.试验结果表明:该方法能够有效发现在微博中传播的食品安全事件,并能过滤掉微博中无关的话题.
As a hot topic, food safety has attracted a lot of attention from the public, and microblog has become the main media platform to expose food safety incidents. Microblog corpus was used as data source with microblog content and user social network behavior characteristics, and the food safety incident discovery method was proposed based on the momentum model. To describe the food safety incident from microblog information flow, the event discovery model was used to detect the candidate feature words related to food safety. The momentum model was established to realize the momentum modeling of candidate feature words and filter the duplicate feature words effectively. The effective feature words were classified and merged by K-means clustering, and the goal of discovering food safety incidents was achieved. The experimental results show that the proposed method can effectively discover the food safety incidents spreading in microblog and filter out irrelevant topics in microblog.
As a hot topic, food safety has attracted a lot of attention from the public, and microblog has become the main media platform to expose food safety incidents. Microblog corpus was used as data source with microblog content and user social network behavior characteristics, and the food safety incident discovery method was proposed based on the momentum model. To describe the food safety incident from microblog information flow, the event discovery model was used to detect the candidate feature words related to food safety. The momentum model was established to realize the momentum modeling of candidate feature words and filter the duplicate feature words effectively. The effective feature words were classified and merged by K-means clustering, and the goal of discovering food safety incidents was achieved. The experimental results show that the proposed method can effectively discover the food safety incidents spreading in microblog and filter out irrelevant topics in microblog.
引文
[ 1 ] 章海亮,孙旭东,刘燕德,等.农产品质量安全可追溯系统的研究进展[J].湖北农业科学学报,2010,49(12):3220-3223.ZHANG H L, SUN X D, LIU Y D, et al. Research progress on agricultural product quality and safety traceability system[J]. Hubei Agricultural Sciences Journal, 2010, 49(12): 3220-3223.(in Chinese)
[ 2 ] 殷俊峰,陶运来,刘铁兵,等.食品可追溯系统建设之初探[J].安徽农业科学学报,2008,36(27):11985-11987,11994.YIN J F, TAO Y L, LIU T B, et al. Preliminary study on the construction of food traceability system [J]. Journal of Anhui Agricultural Sciences, 2008, 36 (27): 11985-11987, 11994. (in Chinese)
[ 3 ] 刘金硕,彭映月,章岚昕,等. 网络食品安全问题话题发现的LDA-K-means算法[J]. 武汉大学学报(工学版), 2017, 50(2):307-310LIU J S, PENG Y Y, ZHANG L X, et al. LDA-K-means algorithm for discovering the topic of network food safety[J]. Journal of Wuhan University (Engineering Science), 2017, 50(2): 307-310. (in Chinese)
[ 4 ] 格桑多吉,乔少杰,韩楠,等. 基于Single-Pass的网络舆情热点发现算法[J]. 电子科技大学学报, 2015,44(4):599-604.GESANG D J, QIAO S J, HAN N, et al. Network-based hotspot discovery algorithm based on Single-Pass[J]. Journal of University of Electronic Science and Technology of China, 2015,44(4): 599-604. (in Chinese)
[ 5 ] 王晓明,王莉,杨敬宗. 微博信息传播网络的结构属性分析[J]. 中文信息学报, 2014, 28(3):55-61.WANG X M, WANG L, YANG J Z. Structural property analysis of weibo information communication network[J]. Chinese Journal of Information Science, 2014, 28(3): 55-61. (in Chinese)
[ 6 ] 李栋,徐志明,李生,等. 在线社会网络中信息扩散[J]. 计算机学报, 2014, 37(1):189-206.LI D, XU Z M, LI S, et al. Information diffusion in online social networks[J]. Chinese Journal of Computers, 2014, 37(1): 189-206. (in Chinese)
[ 7 ] 柏文言,张闯,徐克付,等. 一种融合用户关系的自适应微博话题跟踪方法[J]. 电子学报, 2017, 45(6):1375-1381.BAI W Y, ZHANG C, XU K F, et al. An adaptive microblog topic tracking method based on user relationship[J]. Chinese Journal of Electronics, 2017, 45(6): 1375-1381. (in Chinese)
[ 8 ] 仲兆满,管燕,李存华,等. 微博网络地域Top-k突发事件检测[J]. 计算机学报, 2018,41(7):1504-1516.ZHONG Z M, GUAN Y, LI C H, et al. Detection of Top-k incidents in weibo network region[J]. Chinese Journal of Computers, 2018,41(7):1504-1516. (in Chinese)
[ 9 ] 石磊,杜军平,梁美玉. 基于RNN和主题模型的社交网络突发话题发现[J]. 通信学报, 2018,39(4):189-197. SHI L, DU J P, LIANG M Y. Sudden topic discovery in social networks based on RNN and topic model[J]. Journal of Computation, 2018,39(4):189-197. (in Chinese)
[10] 曹玖新,胥帅,陈高君,等. 在线社交网络中地域性话题发现[J]. 计算机学报, 2017, 40(7):1530-1542.CAO J X, XU S, CHEN G J, et al. Regional topic discovery in online social networks[J]. Chinese Journal of Computers, 2017, 40(7): 1530-1542. (in Chinese)
[11] 尹兰,程飞,任亚峰,等. 基于复杂网络重叠社团发现的微博话题检测[J]. 四川大学学报(自然科学版), 2016, 53(6):1233-1240.YIN L, CHENG F, REN Y F, et al. Detection of microblog topics based on complex network overlap community discovery[J]. Journal of Sichuan University(Natural Science Edition), 2016, 53(6): 1233-1240.(in Chinese)
[12] 刘玉坤,夏栋梁,马丽. 基于AGSO-LSSVM的热点话题预测模型[J]. 重庆邮电大学学报(自然科学版),2014,26(6):803-808.LIU Y K, XIA D L, MA L. Hot topic forecasting model based on AGSO-LSSVM[J]. Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition), 2014, 26(6): 803-808. (in Chinese)
[13] 贺敏,杜攀,张瑾,等. 基于有意义串动量模型的微博突发话题检测方法[J]. 计算机研究与发展, 2015, 52(5): 1022-1028.HE M, DU P,ZHANG J, et al. Microblog bursty topic detection method based on momentum model [J]. Journal of Computer Research and Development, 2015, 52(5):1022-1028. (in Chinese)
[14] HE D, STOTT P. Topic dynamics: an alternative model of bursts in streams of topics[C]//Proc of the 16th ACM Int Conf on Knowledge Discovery and Data Mi-ning. New York: ACM, 2010: 443-452.
[15] 贺敏,徐杰,杜攀,等. 基于时间序列分析的微博突发话题检测方法[J]. 通信学报, 2016, 37(3):48-54.HE M, XU J, DU P, et al. Method of microblog burst topic detection based on time series analysis[J]. Journal of Computation, 2016, 37(3):48-54.(in Chinese)
[16] WAGSTAFF K.Intelligent clustering with instance-level constraints[D].Ithaca:Cornell University,2002.
[17] BAR-HILLEL A,HERTZ T,SHENTAL N, et a1.Lear-ning a mahalanobis metric from equivalence constraints[J].Journal of Machine Learning Research,2005,6:937-965.
[ 2 ] 殷俊峰,陶运来,刘铁兵,等.食品可追溯系统建设之初探[J].安徽农业科学学报,2008,36(27):11985-11987,11994.YIN J F, TAO Y L, LIU T B, et al. Preliminary study on the construction of food traceability system [J]. Journal of Anhui Agricultural Sciences, 2008, 36 (27): 11985-11987, 11994. (in Chinese)
[ 3 ] 刘金硕,彭映月,章岚昕,等. 网络食品安全问题话题发现的LDA-K-means算法[J]. 武汉大学学报(工学版), 2017, 50(2):307-310LIU J S, PENG Y Y, ZHANG L X, et al. LDA-K-means algorithm for discovering the topic of network food safety[J]. Journal of Wuhan University (Engineering Science), 2017, 50(2): 307-310. (in Chinese)
[ 4 ] 格桑多吉,乔少杰,韩楠,等. 基于Single-Pass的网络舆情热点发现算法[J]. 电子科技大学学报, 2015,44(4):599-604.GESANG D J, QIAO S J, HAN N, et al. Network-based hotspot discovery algorithm based on Single-Pass[J]. Journal of University of Electronic Science and Technology of China, 2015,44(4): 599-604. (in Chinese)
[ 5 ] 王晓明,王莉,杨敬宗. 微博信息传播网络的结构属性分析[J]. 中文信息学报, 2014, 28(3):55-61.WANG X M, WANG L, YANG J Z. Structural property analysis of weibo information communication network[J]. Chinese Journal of Information Science, 2014, 28(3): 55-61. (in Chinese)
[ 6 ] 李栋,徐志明,李生,等. 在线社会网络中信息扩散[J]. 计算机学报, 2014, 37(1):189-206.LI D, XU Z M, LI S, et al. Information diffusion in online social networks[J]. Chinese Journal of Computers, 2014, 37(1): 189-206. (in Chinese)
[ 7 ] 柏文言,张闯,徐克付,等. 一种融合用户关系的自适应微博话题跟踪方法[J]. 电子学报, 2017, 45(6):1375-1381.BAI W Y, ZHANG C, XU K F, et al. An adaptive microblog topic tracking method based on user relationship[J]. Chinese Journal of Electronics, 2017, 45(6): 1375-1381. (in Chinese)
[ 8 ] 仲兆满,管燕,李存华,等. 微博网络地域Top-k突发事件检测[J]. 计算机学报, 2018,41(7):1504-1516.ZHONG Z M, GUAN Y, LI C H, et al. Detection of Top-k incidents in weibo network region[J]. Chinese Journal of Computers, 2018,41(7):1504-1516. (in Chinese)
[ 9 ] 石磊,杜军平,梁美玉. 基于RNN和主题模型的社交网络突发话题发现[J]. 通信学报, 2018,39(4):189-197. SHI L, DU J P, LIANG M Y. Sudden topic discovery in social networks based on RNN and topic model[J]. Journal of Computation, 2018,39(4):189-197. (in Chinese)
[10] 曹玖新,胥帅,陈高君,等. 在线社交网络中地域性话题发现[J]. 计算机学报, 2017, 40(7):1530-1542.CAO J X, XU S, CHEN G J, et al. Regional topic discovery in online social networks[J]. Chinese Journal of Computers, 2017, 40(7): 1530-1542. (in Chinese)
[11] 尹兰,程飞,任亚峰,等. 基于复杂网络重叠社团发现的微博话题检测[J]. 四川大学学报(自然科学版), 2016, 53(6):1233-1240.YIN L, CHENG F, REN Y F, et al. Detection of microblog topics based on complex network overlap community discovery[J]. Journal of Sichuan University(Natural Science Edition), 2016, 53(6): 1233-1240.(in Chinese)
[12] 刘玉坤,夏栋梁,马丽. 基于AGSO-LSSVM的热点话题预测模型[J]. 重庆邮电大学学报(自然科学版),2014,26(6):803-808.LIU Y K, XIA D L, MA L. Hot topic forecasting model based on AGSO-LSSVM[J]. Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition), 2014, 26(6): 803-808. (in Chinese)
[13] 贺敏,杜攀,张瑾,等. 基于有意义串动量模型的微博突发话题检测方法[J]. 计算机研究与发展, 2015, 52(5): 1022-1028.HE M, DU P,ZHANG J, et al. Microblog bursty topic detection method based on momentum model [J]. Journal of Computer Research and Development, 2015, 52(5):1022-1028. (in Chinese)
[14] HE D, STOTT P. Topic dynamics: an alternative model of bursts in streams of topics[C]//Proc of the 16th ACM Int Conf on Knowledge Discovery and Data Mi-ning. New York: ACM, 2010: 443-452.
[15] 贺敏,徐杰,杜攀,等. 基于时间序列分析的微博突发话题检测方法[J]. 通信学报, 2016, 37(3):48-54.HE M, XU J, DU P, et al. Method of microblog burst topic detection based on time series analysis[J]. Journal of Computation, 2016, 37(3):48-54.(in Chinese)
[16] WAGSTAFF K.Intelligent clustering with instance-level constraints[D].Ithaca:Cornell University,2002.
[17] BAR-HILLEL A,HERTZ T,SHENTAL N, et a1.Lear-ning a mahalanobis metric from equivalence constraints[J].Journal of Machine Learning Research,2005,6:937-965.