@inproceedings{thakar-etal-2026-sentiment,
title = "Sentiment Analysis of Yelp Review Dataset: A Comparative Study of Machine Learning Methods",
author = "Thakar, Krishna and
Abu Sheha, Mohamed and
Thompson, Emmanuel",
editor = "T.Y.S.S., Santosh and
Rodriguez, Juan Diego and
de Gibert, Ona",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-srw.38/",
pages = "428--437",
ISBN = "979-8-89176-393-7",
abstract = {Sentiment analysis involves analyzing text to determine whether the sentiment expressed is positive, negative, or neutral. In the context of online reviews, such as those on Yelp, sentiment analysis helps businesses assess customer satisfaction and identify areas for improvement. Given the large volume of user-generated content, restaurants often struggle to extract actionable insights from feedback, making sentiment analysis an efficient tool for categorizing reviews and highlighting customer concerns. This study focuses on sentiment analysis of Yelp reviews. The main research question is: How can Natural Language Processing (NLP) combined with statistical machine learning methods be applied to classify sentiment in Yelp reviews and provide actionable insights for improving customer satisfaction, service quality, and business performance? The study used 21,000 Yelp reviews, utilizing NLP approaches - tokenization, stop-word removal, and vectorization. Comparative classification predictive modeling and analysis were done across traditional machine learning (Logistic Regression, Support Vector Machine (SVM), Na{\"i}ve Bayes, Random Forest), deep learning methods (CNN, LSTM, BiLSTM, GRU, RNN), and an advanced transformer-based (RoBERTa) model. Results showed that RoBERTa outperformed the other candidate methods. These findings highlight the potential of advanced NLP techniques to offer businesses practical ways to address customer complaints, enhance service quality, and drive overall business performance.}
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thakar-etal-2026-sentiment">
<titleInfo>
<title>Sentiment Analysis of Yelp Review Dataset: A Comparative Study of Machine Learning Methods</title>
</titleInfo>
<name type="personal">
<namePart type="given">Krishna</namePart>
<namePart type="family">Thakar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Abu Sheha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuel</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.Y.S.S.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Diego</namePart>
<namePart type="family">Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ona</namePart>
<namePart type="family">de Gibert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-393-7</identifier>
</relatedItem>
<abstract>Sentiment analysis involves analyzing text to determine whether the sentiment expressed is positive, negative, or neutral. In the context of online reviews, such as those on Yelp, sentiment analysis helps businesses assess customer satisfaction and identify areas for improvement. Given the large volume of user-generated content, restaurants often struggle to extract actionable insights from feedback, making sentiment analysis an efficient tool for categorizing reviews and highlighting customer concerns. This study focuses on sentiment analysis of Yelp reviews. The main research question is: How can Natural Language Processing (NLP) combined with statistical machine learning methods be applied to classify sentiment in Yelp reviews and provide actionable insights for improving customer satisfaction, service quality, and business performance? The study used 21,000 Yelp reviews, utilizing NLP approaches - tokenization, stop-word removal, and vectorization. Comparative classification predictive modeling and analysis were done across traditional machine learning (Logistic Regression, Support Vector Machine (SVM), Naïve Bayes, Random Forest), deep learning methods (CNN, LSTM, BiLSTM, GRU, RNN), and an advanced transformer-based (RoBERTa) model. Results showed that RoBERTa outperformed the other candidate methods. These findings highlight the potential of advanced NLP techniques to offer businesses practical ways to address customer complaints, enhance service quality, and drive overall business performance.</abstract>
<identifier type="citekey">thakar-etal-2026-sentiment</identifier>
<location>
<url>https://aclanthology.org/2026.acl-srw.38/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>428</start>
<end>437</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sentiment Analysis of Yelp Review Dataset: A Comparative Study of Machine Learning Methods
%A Thakar, Krishna
%A Abu Sheha, Mohamed
%A Thompson, Emmanuel
%Y T.Y.S.S., Santosh
%Y Rodriguez, Juan Diego
%Y de Gibert, Ona
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-393-7
%F thakar-etal-2026-sentiment
%X Sentiment analysis involves analyzing text to determine whether the sentiment expressed is positive, negative, or neutral. In the context of online reviews, such as those on Yelp, sentiment analysis helps businesses assess customer satisfaction and identify areas for improvement. Given the large volume of user-generated content, restaurants often struggle to extract actionable insights from feedback, making sentiment analysis an efficient tool for categorizing reviews and highlighting customer concerns. This study focuses on sentiment analysis of Yelp reviews. The main research question is: How can Natural Language Processing (NLP) combined with statistical machine learning methods be applied to classify sentiment in Yelp reviews and provide actionable insights for improving customer satisfaction, service quality, and business performance? The study used 21,000 Yelp reviews, utilizing NLP approaches - tokenization, stop-word removal, and vectorization. Comparative classification predictive modeling and analysis were done across traditional machine learning (Logistic Regression, Support Vector Machine (SVM), Naïve Bayes, Random Forest), deep learning methods (CNN, LSTM, BiLSTM, GRU, RNN), and an advanced transformer-based (RoBERTa) model. Results showed that RoBERTa outperformed the other candidate methods. These findings highlight the potential of advanced NLP techniques to offer businesses practical ways to address customer complaints, enhance service quality, and drive overall business performance.
%U https://aclanthology.org/2026.acl-srw.38/
%P 428-437
Markdown (Informal)
[Sentiment Analysis of Yelp Review Dataset: A Comparative Study of Machine Learning Methods](https://aclanthology.org/2026.acl-srw.38/) (Thakar et al., ACL 2026)
ACL