Paper: AttitudeMiner: Mining Attitude from Online Discussions

ACL ID N12-3009
Title AttitudeMiner: Mining Attitude from Online Discussions
Venue Annual Conference of the North American Chapter of the Association for Computational Linguistics
Session System Demonstration
Year 2012
Authors

This demonstration presents AttitudeMiner, a system for mining attitude from online dis- cussions. AttitudeMiner uses linguistic tech- niques to analyze the text exchanged between participants of online discussion threads at dif- ferent levels of granularity: the word level, the sentence level, the post level, and the thread level. The goal of this analysis is to iden- tify the polarity of the attitude the discussants carry towards one another. Attitude predic- tions are used to construct a signed network representation of the discussion thread. In this network, each discussant is represented by a node. An edge connects two discussants if they exchanged posts. The sign (positive or negative) of the edge is set based on the po- larity of the attitude identified in the text asso- ciated with...