Performance Comparison of Deep Learning Text Embeddings in Sentiment Analysis Tasks with Online Consumer Reviews

Ziyi Yang, Patrick Cheong Iao Pang, Ho Yin Kan

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

Abstract

In order to investigate the effect of various natural language processing models on different data processing, this paper adopted the consumer reviews of two well-known Internet retailing websites: Yelp and Zappos, and used four text embedding methods: word2vec, Glove, BERT, and GPT-2 and two text classification methods: SVM and Neural Network (NN) for text classification, in order to compare the performance of the combinations of these text mining techniques. The result shows that BERT is the best-performing text embedding method overall in both datasets when used with both SVM and NN. It is also found that NN is better than SVM for overall text classification. As an exploratory experiment, we aim to provide a three-dimensional comparison to find the most suitable algorithm for consumer review data, and the implication is that BERT and NN can achieve satisfactory results in most of the scenarios.

Original languageEnglish
Title of host publicationProceedings of the 2022 10th International Conference on Information Technology
Subtitle of host publicationIoT and Smart City, ICIT 2022
PublisherAssociation for Computing Machinery
Pages1-7
Number of pages7
ISBN (Electronic)9781450397438
DOIs
Publication statusPublished - 23 Dec 2022
Event10th International Conference on Information Technology: IoT and Smart City, ICIT 2022 - Virtual, Online, China
Duration: 23 Dec 202226 Dec 2022

Publication series

NameACM International Conference Proceeding Series

Conference

Conference10th International Conference on Information Technology: IoT and Smart City, ICIT 2022
Country/TerritoryChina
CityVirtual, Online
Period23/12/2226/12/22

Keywords

  • business analytics
  • deep learning
  • online consumer reviews
  • text embedding

Fingerprint

Dive into the research topics of 'Performance Comparison of Deep Learning Text Embeddings in Sentiment Analysis Tasks with Online Consumer Reviews'. Together they form a unique fingerprint.

Cite this