A Hybrid Deep Learning Model to Predict Business Closure from Reviews and User Attributes Using Sentiment Aligned Topic Model

Thazhackal, Sharun S and Devi, Susheela V (2018) A Hybrid Deep Learning Model to Predict Business Closure from Reviews and User Attributes Using Sentiment Aligned Topic Model. In: 2018 IEEE Symposium Series On Computational Intelligence (IEEE SSCI), NOV 18-21, 2018, Bengaluru, INDIA, pp. 397-404.

PDF deeplearn-2018-accepted.pdf - Published Version Restricted to Registered users only Download (473kB) | Request a copy

Abstract

Business closure is a very good indicator for success or failure of a business. This will help investors and banks as to whether to invest or lend to a particular business for future growth and benefits. Traditional machine learning techniques require extensive manual feature engineering and still do not perform satisfactorily due to significant class imbalance problem and little difference in the attributes for open and closed businesses. We have used historical data besides taking care of the class imbalance problem. Transfer learning also has been used to tackle the issue of having small categorical dalasets. A hybrid deep learning model has been proposed to predict whether a business would be shut down within a specific period of time. Sentiment Aligned Topic Model (SATM) is used to extract aspect-wise sentiment scores from user reviews. Our results show a marked improvement over traditional machine learning techniques. It also shows how the aspect-wise sentiment scores corresponding to each business, computed using SATM, help to give better results.

Item Type:	Conference Proceedings
Publisher:	IEEE
Additional Information:	8th IEEE Symposium Series on Computational Intelligence (IEEE SSCI), Bengaluru, INDIA, NOV 18-21, 2018
Keywords:	business closure prediction; sentiment aligned topic model; NLP; lexicon generation; apsect-wise ratings; yelp; review analysis; deep learning; hybrid neural network; CNN
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	15 Mar 2019 05:02
Last Modified:	16 Mar 2019 06:15
URI:	http://eprints.iisc.ac.in/id/eprint/61954

Actions (login required)

View Item