Tampere University of Technology

TUTCRIS Research Portal

BL-LDA: Bringing bigram to supervised topic model

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publicationProceedings - 2015 International Conference on Computational Science and Computational Intelligence, CSCI 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages83-88
Number of pages6
ISBN (Electronic)9781467397957
DOIs
Publication statusPublished - 2 Mar 2016
Publication typeA4 Article in a conference publication
EventInternational Conference on Computational Science and Computational Intelligence, CSCI 2015 - Las Vegas, United States
Duration: 7 Dec 20159 Dec 2015

Conference

ConferenceInternational Conference on Computational Science and Computational Intelligence, CSCI 2015
CountryUnited States
CityLas Vegas
Period7/12/159/12/15

Abstract

With the increasing amount of data being published on the Web, it is difficult to analyze their content within a short time. Topic modeling techniques can summarize textual data that contains several topics. Both the label (such as category or tag) and word co-occurrence play a significant role in understanding textual data. However, many conventional topic modeling techniques are limited to the bag-of-words assumption. In this paper, we develop a probabilistic model called Bigram Labeled Latent Dirichlet Allocation (BL-LDA), to address the limitation of the bag-of-words assumption. The proposed BL-LDA incorporates the bigram into the Labeled LDA (L-LDA) technique. Extensive experiments on Yelp data show that the proposed scheme is better than the L-LDA in terms of accuracy.

Keywords

  • Data Analysis, Data Mining, Text Classification, Topic Modeling