Opinion retrieval experiments using generative models: Experiments for the TREC 2006 blog track

Koji Eguchi, Chirag Shah

Research output: Contribution to journalConference articlepeer-review

1 Scopus citations

Abstract

Ranking blog posts that express opinions regarding a given topic should serve a critical function in helping users. We explored three types of opinion retrieval methods in the framework of probabilistic language models. The first method combines topic-relevance model and opinion-relevance model that captures topic dependence of the opinion expressions. The second method makes use of probability that any of opinion-bearing words appear in each target document as document prior probability in query-likelihood model. The third method makes use of probability that any of adjectives or adverbs appear in each target document as document prior probability, assuming opinionated documents tend to contain more adjectives or adverbs than other documents.

Original languageEnglish (US)
JournalNIST Special Publication
StatePublished - 2006
Externally publishedYes
Event15th Text REtrieval Conference, TREC 2006 - Gaithersburg, MD, United States
Duration: Nov 14 2006Nov 17 2006

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Fingerprint

Dive into the research topics of 'Opinion retrieval experiments using generative models: Experiments for the TREC 2006 blog track'. Together they form a unique fingerprint.

Cite this