Universal, unsupervised (rule-based), uncovered sentiment analysis
详细信息 查看全文
- 作者：David Vilares ; david.vilares@udc.es ; Carlos Gó ; mez-Rodrí ; guez carlos.gomez@udc.es ; Miguel A. Alonso miguel.alonso@udc.es
- 关键词：Sentiment analysis ; Multilingual ; Dependency parsing ; Natural language processing
- 刊名：Knowledge-Based Systems
- 出版年：2017
- 出版时间：15 February 2017
- 年：2017
- 卷：118
- 期：Complete
- 页码：45-55
- 全文大小：2104 K
- 卷排序：118
文摘
We present a novel unsupervised approach for multilingual sentiment analysis driven by compositional syntax-based rules. On the one hand, we exploit some of the main advantages of unsupervised algorithms: (1) the interpretability of their output, in contrast with most supervised models, which behave as a black box and (2) their robustness across different corpora and domains. On the other hand, by introducing the concept of compositional operations and exploiting syntactic information in the form of universal dependencies, we tackle one of their main drawbacks: their rigidity on data that are structured differently depending on the language concerned. Experiments show an improvement both over existing unsupervised methods, and over state-of-the-art supervised models when evaluating outside their corpus of origin. Experiments also show how the same compositional operations can be shared across languages. The system is available at http://www.grupolys.org/software/UUUSA/.