Paper: Entities' Sentiment Relevance

ACL ID P14-2015
Title Entities' Sentiment Relevance
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014

Sentiment relevance detection problems oc- cur when there is a sentiment expression in a text, and there is the question of whether or not the expression is related to a given entity or, more generally, to a given situation. The paper discusses variants of the problem, and shows that it is distinct from other somewhat similar problems occurring in the field of sen- timent analysis and opinion mining. We ex- perimentally demonstrate that using the in- formation about relevancy significantly af- fects the final sentiment evaluation of the en- tities. We then compare a set of different al- gorithms for solving the relevance detection problem. The most accurate results are achieved by algorithms that use certain doc- ument-level information about the target enti- ties. We show that thi...