relation: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/1545/
title: Hidden Topic Models for Multi-Label Review Classification: An Experimental Study
creator: Pham, Thi Ngan
creator: Phan, Thi Thom
creator: Nguyen, Phuoc Thao
creator: Ha, Quang Thuy
subject: Information Technology (IT)
description: In recent years, Multi-Label Classification (MLC) has become an important task in the field of Supervised Learning. The MLC tasks are omnipresent in real-world problems in which an instance could belong to different classes simultaneously. In this paper, we presented a method for MLC using the hidden topic method to enrich the data features and using mutual information for feature selection. Our experiments on classifying user reviews about one thousand Vietnamese hotels showed the efficacy of the proposed approach.
date: 2016-03-26
type: Conference or Workshop Item
type: NonPeerReviewed
format: application/pdf
language: en
identifier: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/1545/1/NCS%20Ph%E1%BA%A1m%20Th%E1%BB%8B%20Ng%C3%A2n%20-%20QH2012%20-%20poster.pdf
identifier:   Pham, Thi Ngan and Phan, Thi Thom and Nguyen, Phuoc Thao and Ha, Quang Thuy  (2016) Hidden Topic Models for Multi-Label Review Classification: An Experimental Study.  In: SW4PHD: the 2016 Scientific Workshop for PhD Students, 26 March 2016, Hanoi.