Difficulties and Improvements to Graph-Based Lexical Sentiment Analysis Using LISA

Abstract

Lexical sentiment analysis (LSA) underlines a family of methods combining natural language processing, machine learning, or graph navigation techniques to identify the underlying sentiments or emotions carried in textual data. In this paper, we introduce LISA, an unsupervised word-level knowledge graph-based LexIcal Sentiment Analysis framework. It uses different variants of shortest path graph navigation techniques to compute and propagate affective scores in a lexical-affective graph (LAG), created by connecting a typical lexical knowledgebase (KB) like WordNet, with a reliable affect KB like WordNet-Affect Hierarchy. LISA was designed in two consecutive iterations, producing two main modules: i) LISA 1.0 for affect navigation, and ii) LISA 2.0 for affect propagation and lookup. LISA 1.0 suffered from the semantic connectivity problem shared by some existing lexicon-based methods, and required polynomial execution time. This led to the development of LISA 2.0, which i) processes affective relationships separately from lexical/semantic connections (solving the semantic connectivity problem of LISA 1.0), and ii) produces a sentiment lexicon which can be searched in logarithmic time (handling LISA 1.0's efficiency problem). Experimental results on the ANEW dataset show that LISA 2.0, while completely unsupervised, is on a par with existing supervised solutions, highlighting its quality and potential.