Integrating Argumentation and Sentiment Analysis for Mining Opinions from Twitter

KATHRIN GROSSE; MARÍA PAULA GONZÁLEZ; CARLOS IVÁN CHESÑEVAR; ANA MAGUITMAN

AI COMMUNICATIONS

IOS PRESS

Lugar: Amsterdam; Año: 2015 vol. 28 p. 387 - 401

0921-7126

Social networks have grown exponentially in use and impact on the society as a whole. In particular, mi- croblogging platforms such as Twitter have become im- portant tools to assess public opinion on dierent is- sues. Recently, some approaches for assessing Twitter messages have been developed, identifying sentiments associated with relevant keywords or hashtags. How- ever, such approaches have an important limitation, as they do not take into account contradictory and po- tentially inconsistent information which might emerge from relevant messages. We contend that the informa- tion made available in Twitter can be useful to extract a particular version of arguments (called opinions" in our formalization) which emerge bottom-up from the social interaction associated with such messages. In this paper we present a novel framework which al- lows to mine opinions from Twitter based on incre- mentally generated queries. As a result, we will be able to obtain an opinion tree", rooted in the rst original query. Distinguished, con icting elements in an opin- ion tree lead to so-called con ict trees", which resem- ble dialectical trees as those used traditionally in de- feasible argumentation.