Genetic programming for domain adaptation in product reviews

Chaturvedi, Iti, Cambria, Erik, Cavallari, Sandro, and Welsch, Roy E. (2020) Genetic programming for domain adaptation in product reviews. In: Proceedings of the IEEE Congress on Evolutionary Computation. From: CEC 2020: IEEE Congress on Evolutionary Computation, 19-24 July 2020, Glasgow, UK.

[img] PDF - Accepted Version
Restricted to Repository staff only

[img] PDF (Published Version) - Published Version
Restricted to Repository staff only

View at Publisher Website:


There is a large variety of products sold online and the websites are in several languages. Hence, it is desirable to train a model that can predict sentiments in different domains simultaneously. Previous authors have used deep learning to extract features from multiple domains. Here, each word is represented by a vector that is determined using co-occurrence data. Such a model requires that all sentences have the same length resulting in low accuracy. To overcome this challenge, we model the features in each sentence using a variable length tree called a Genetic Program. The polarity of clauses can be represented using mathematical operators such as '+' or '-' at internal nodes in the tree. The proposed model is evaluated on Amazon product reviews for different products and in different languages. We are able to outperform the accuracy of baseline multi-domain models in the range of 5-20%.

Item ID: 64484
Item Type: Conference Item (Research - E1)
ISBN: 978-1-7281-6929-3
Keywords: Genetic Programming; Sentiment Analysis
Date Deposited: 30 Sep 2020 06:10
FoR Codes: 46 INFORMATION AND COMPUTING SCIENCES > 4602 Artificial intelligence > 460208 Natural language processing @ 70%
52 PSYCHOLOGY > 5299 Other psychology > 529999 Other psychology not elsewhere classified @ 30%
SEO Codes: 97 EXPANDING KNOWLEDGE > 970109 Expanding Knowledge in Engineering @ 70%
90 COMMERCIAL SERVICES AND TOURISM > 9003 Tourism > 900302 Socio-Cultural Issues in Tourism @ 30%
Downloads: Total: 3
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page