Open AccessFusion approach to finding opinionated blogs
Author(s) -
Yang Kiduk,
Yu Ning,
Valerio Alejandro,
Zhang Hui,
Ke Weimao
Publication year - 2007
Publication title -
proceedings of the american society for information science and technology
Language(s) - English
Resource type - Journals
eISSN - 1550-8390
pISSN - 0044-7870
DOI - 10.1002/meet.1450440254
Subject(s) - sentiment analysis , computer science , adjective , natural language processing , information retrieval , term (time) , expert opinion , artificial intelligence , similarity (geometry) , verb , computational linguistics , linguistics , noun , medicine , philosophy , physics , quantum mechanics , intensive care medicine , image (mathematics)
In this paper, we describe a fusion approach to finding opinionated blog postings. Our approach to opinion blog retrieval consisted of first applying traditional IR methods to retrieve on‐topic blogs and then boosting the ranks of opinionated blogs based on combined opinion scores generated by multiple assessment methods. Our opinion module is composed of the Opinion Term Module, which identifies opinions based on the frequency of opinion terms (i.e., terms that occur frequently in opinion blogs), the Rare Term Module, which uses uncommon/rare terms (e.g., “sooo good”) for opinion classification, the IU Module, which uses IU (I and you) collocations, and the Adjective‐Verb Module, which uses computational linguistics' distribution similarity approach to learn the subjective language from training data.