Sentiment Classification and Visualization of Product Review Data

Piazza A, Davcheva P (2016)

Publication Language: English

Publication Type: Book chapter / Article in edited volumes

Publication year: 2016

Publisher: Chapman & Hall/CRC Data Mining and Knowledge Discovery Series

Edited Volumes: Text Mining, Web Mining, and Visualization Use Cases Using Open Source Tools

Series: Chapman & Hall/CRC Data Mining and Knowledge Discovery Series

City/Town: Boca Raton, USA

ISBN: 9781482237573

Abstract

The chapter presents a process for sentiment classification of product review data. Our dataset consists of reviews on six categories of products from amazon.com. We use the star review system to determine whether the review is positive or negative. Emoticons substitution, tokenization, stopwords removal, and text normalization are applied, features are generated, which then are used for training the classifier. The resulting classifier is evaluated based on a k-fold stratified cross-validation strategy using the accuracy and a confusion matrix as measure for determining the quality of the prediction. As a final step, we demonstrate two visualization techniques to reveal the context behind the sentiment.

Authors with CRIS profile

Alexander Piazza Lehrstuhl für Wirtschaftsinformatik, insbesondere im Dienstleistungsbereich Pavlina Kröckel Lehrstuhl für Wirtschaftsinformatik, insbesondere im Dienstleistungsbereich

How to cite

APA:

Piazza, A., & Davcheva, P. (2016). Sentiment Classification and Visualization of Product Review Data. In Hofmann, M., Chisholm, A. (Eds.), Text Mining, Web Mining, and Visualization Use Cases Using Open Source Tools. Boca Raton, USA: Chapman & Hall/CRC Data Mining and Knowledge Discovery Series.

MLA:

Piazza, Alexander, and Pavlina Davcheva. "Sentiment Classification and Visualization of Product Review Data." Text Mining, Web Mining, and Visualization Use Cases Using Open Source Tools. Ed. Hofmann, M., Chisholm, A., Boca Raton, USA: Chapman & Hall/CRC Data Mining and Knowledge Discovery Series, 2016.

BibTeX: Download