Welcome to the InfoSci Platform
Sentiment Weighted Word Embedding for Big Text Data

Sentiment Weighted Word Embedding for Big Text Data

Jenish Dhanani, Rupa Mehta, Dipti Rana
Copyright: © 2021 |Volume: 16 |Issue: 6 |Pages: 17
ISSN: 1548-1093|EISSN: 1548-1107|EISBN13: 9781799867425|DOI: 10.4018/IJWLTT.20211101.oa2
Cite Article Cite Article

MLA

Dhanani, Jenish, et al. "Sentiment Weighted Word Embedding for Big Text Data." IJWLTT vol.16, no.6 2021: pp.1-17. http://doi.org/10.4018/IJWLTT.20211101.oa2

APA

Dhanani, J., Mehta, R., & Rana, D. (2021). Sentiment Weighted Word Embedding for Big Text Data. International Journal of Web-Based Learning and Teaching Technologies (IJWLTT), 16(6), 1-17. http://doi.org/10.4018/IJWLTT.20211101.oa2

Chicago

Dhanani, Jenish, Rupa Mehta, and Dipti Rana. "Sentiment Weighted Word Embedding for Big Text Data," International Journal of Web-Based Learning and Teaching Technologies (IJWLTT) 16, no.6: 1-17. http://doi.org/10.4018/IJWLTT.20211101.oa2

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Sentiment analysis is the practice of eliciting a sentiment orientation of people's opinions (i.e. positive, negative and neutral) toward the specific entity. Word embedding technique like Word2vec is an effective approach to encode text data into real-valued semantic feature vectors. However, it fails to preserve sentiment information that results in performance deterioration for sentiment analysis. Additionally, big sized textual data consisting of large vocabulary and its associated feature vectors demands huge memory and computing power. To overcome these challenges, this research proposed a MapReduce based Sentiment weighted Word2Vec (MSW2V), which learns the sentiment and semantic feature vectors using sentiment dictionary and big textual data in a distributed MapReduce environment, where memory and computing power of multiple computing nodes are integrated to accomplish the huge resource demand. Experimental results demonstrate the outperforming performance of the MSW2V compared to the existing distributed and non-distributed approaches.