Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Identifying complaints from product reviews: a case study on Hindi

Singh, Raghvendra Pratap, Haque, Rejwanul orcid logoORCID: 0000-0003-1680-0099, Hasanuzzaman, Mohammed orcid logoORCID: 0000-0003-1838-0091 and Way, Andy orcid logoORCID: 0000-0001-5736-5930 (2020) Identifying complaints from product reviews: a case study on Hindi. In: 28th Irish Conference on Artificial Intelligence and Cognitive Science, 7-8 Dec 2020, Dublin, Ireland.

Abstract
When an expectation does not meet reality in a real-world situation, the difference is usually expressed and communicated via an act which is complaint. Customers often post reviews on the products or services they purchase on the retailer websites and different social media platforms, and the reviews may reflect complaints about the products or services. Automatic recognition of customers’ complaints on products or services that they purchase can be crucial for the organizations, multinationals and online retailers since they can exploit this information to fulfil the customers’ expectations including managing and resolving the complaints. In this work, we present the supervised and semi-supervised learning strategies to identify users’ complaints from the language they use to post their reviews. In other words, we automatically identify complaints from the opinionated texts (reviews) about products posted in Hindi. For this, first we automatically crawled the Hindi reviews on different products from the the websites of the retail giant Amazon and the popular social media platform YouTube, and prepared a gold-standard data set via a systematic manual annotation process. We use state-of-the-art classification algorithms for the complaints identification task and our classification models achieve reasonable classification accuracy (F1 = 68.38%) on a gold-standard evaluation test set.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Additional Information:This paper was presented in student track of AICS2020 from the practicum of M.Sc. in Computing, Dublin City University
Uncontrolled Keywords:Random walk; LSTM; fastText;Dice coefficient; SMOTE
Subjects:Computer Science > Artificial intelligence
Computer Science > Computational linguistics
Computer Science > Machine learning
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > ADAPT
Published in: Proceedings of The 28th Irish Conference on Artificial Intelligence and Cognitive Science AICS 2020. 2771. CUER-WS.
Publisher:CUER-WS
Official URL:http://ceur-ws.org/Vol-2771/AICS2020_paper_28.pdf
Copyright Information:© 2020 The Authors CC- 0 (Open Access)
ID Code:25290
Deposited On:04 Jan 2021 13:32 by Raghvendra Pratap Singh . Last Modified 11 May 2023 14:26
Documents

Full text available as:

[thumbnail of AICS2020_paper_28.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
121kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record