Informatique de Toulouse,

Most past work on determining the strength of subjective expres-sions within a sentence or a document use specific parts of speech such as adjectives, verbs and nouns. To date, there is almost no work on the use of adverbs in sentiment analysis, nor has there been any work on the use of adverb-adjective combinations (AACs). We propose an AAC-based sentiment analysis technique that uses a lin-guistic analysis of adverbs of degree. We define a set of general axioms (based on a classification of adverbs of degree into five cat-egories) that all adverb scoring techniques must satisfy. Instead of aggregating scores of both adverbs and adjectives using simple scor-ing functions, we propose an axiomatic treatment of AACs based on the linguistic classification of adverbs. Three specific AAC scor-ing methods that satisfy the axioms are presented. We describe the results of experiments on an annotated set of 200 news articles (an-notated by 10 students) and compare our algorithms with some exist-ing sentiment analysis algorithms. We show that our results lead to higher accuracy based on Pearson correlation with human subjects