Universal, unsupervised (rule-based), uncovered sentiment analysis

• DOI: 10.1016/j.knosys.2016.11.014
• Publication Date: 2016-11-23T07:00:53Z
• Authors: David Vilares; Carlos Gómez-Rodr...; Miguel A. Alonso
• Keywords: FOS: Computer and information sciences; Sentiment analysis; Computer Science - Computation and Language; Natural language processing; Multilingual; 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology; Dependency parsing; Computation and Language (cs.CL)

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/<br/>19 pages, 5 Tables, 6 Figures. This is the authors version of a work that was accepted for publication in Knowledge-Based Systems<br/>