Linguistically motivated Language Resources for Sentiment Analysis

Abstract

Computational approaches to sentiment analysis focus on the identification, extraction, summarization and visualization of emotion and opinion expressed in texts. These tasks require large-scale language resources (LRs) developed either manually or semi-automatically. Building them from scratch, however, is a laborious and costly task, and re-using and repurposing already existing ones is a solution to this bottleneck. We hereby present work aimed at the extension and enrichment of existing general-purpose LRs, namely a set of computational lexica, and their integration in a new emotion lexicon that would be applicable for a number of Natural Language Processing applications beyond mere syntactic parsing.