Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
166 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A systematic literature review on machine learning applications for consumer sentiment analysis using online reviews (2008.10282v1)

Published 24 Aug 2020 in cs.HC

Abstract: Consumer sentiment analysis is a recent fad for social media related applications such as healthcare, crime, finance, travel, and academics. Disentangling consumer perception to gain insight into the desired objective and reviews is significant. With the advancement of technology, a massive amount of social web-data increasing in terms of volume, subjectivity, and heterogeneity, becomes challenging to process it manually. Machine learning techniques have been utilized to handle this difficulty in real-life applications. This paper presents the study to find out the usefulness, scope, and applicability of this alliance of Machine Learning techniques for consumer sentiment analysis on online reviews in the domain of hospitality and tourism. We have shown a systematic literature review to compare, analyze, explore, and understand the attempts and direction in a proper way to find research gaps to illustrating the future scope of this pairing. This work is contributing to the extant literature in two ways; firstly, the primary objective is to read and analyze the use of machine learning techniques for consumer sentiment analysis on online reviews in the domain of hospitality and tourism. Secondly, in this work, we presented a systematic approach to identify, collect observational evidence, results from the analysis, and assimilate observations of all related high-quality research to address particular research queries referring to the described research area.

Citations (206)

Summary

  • The paper demonstrates the effectiveness of ML models like SVM and Naive Bayes in automating consumer sentiment analysis from online reviews.
  • It introduces a conceptual ML-CSA framework covering data collection, preprocessing, and analysis to support actionable insights for the hospitality and tourism sectors.
  • It identifies emerging research opportunities such as reinforcement learning applications and incorporating multilingual reviews to capture diverse consumer sentiments.

Systematic Literature Review on Machine Learning Applications for Consumer Sentiment Analysis Using Online Reviews

The paper "A systematic literature review on machine learning applications for consumer sentiment analysis using online reviews" explores the integration of Machine Learning (ML) techniques in analyzing consumer sentiments derived from online reviews, specifically within the hospitality and tourism sectors. The authors, Praphula Kumar Jain and Rajendra Pamula, underscore the complexity of processing voluminous and heterogeneous data manually, which propels the need for automated ML-based sentiment analysis.

Overview

The paper delineates the significance of Consumer Sentiment Analysis (CSA) in extracting actionable insights relevant to organizational growth and consumer satisfaction. Moreover, it introduces ML methodologies as pivotal tools in disentangling consumer perceptions, thereby facilitating effective sentiment classification, predictive recommendations, and fake review detection. This systematic review serves the dual purpose of elucidating existing literature on ML applications in CSA and identifying research gaps that pave the way for further exploration.

Key Findings

The review encompasses a diverse array of ML techniques, such as Decision Trees (DT), Support Vector Machine (SVM), Neural Networks (NN), and Logistic Regression (LR), which are frequently employed to enhance sentiment classification accuracy. Notably, regression models, SVM, and Naive Bayes (NB) algorithms are prominently utilized across various studies, highlighting their efficacy in sentiment determination. Moreover, the review identifies clustering and hybrid models as emerging areas that merit future research focus.

In terms of datasets, the paper notes a prevalent reliance on reviews from platforms such as TripAdvisor, Yelp, and Skytrax, which offer rich textual data from hotels and airlines. This indicates a potential research opportunity for researchers to delve into reviews from museums and historical sites, thus broadening the domain of CSA application.

Practical Implications

The authors propose a conceptual framework for ML-CSA, which systematically guides researchers in leveraging ML techniques to uncover insights from unstructured online reviews. The framework encompasses data collection, preprocessing, and ML application phases, culminating in decision-making strategies that organizations can employ to enhance consumer experiences and refine service offerings.

For practitioners in the hospitality and tourism industry, the implications are manifold. Accurate sentiment analysis can illuminate pivotal service attributes that affect consumer satisfaction and inform policy adjustments. This supports the development of targeted marketing strategies and the implementation of customer-centric service improvements.

Theoretical Implications and Future Directions

From a theoretical standpoint, the integration of ML technologies into sentiment analysis exemplifies a methodological advancement that enhances the depth and accuracy of consumer behavior research. The paper encourages the exploration of reinforcement learning techniques and the development of adaptive sentiment analysis tools that can cater to non-textual data, such as audio or video reviews.

Furthermore, the authors suggest expanding the linguistic scope of studies by incorporating online reviews in various languages beyond English, thereby addressing cultural factors that may influence consumer sentiment differently.

Conclusion

The paper successfully underscores the transformational impact of ML in the domain of consumer sentiment analysis, especially within the hospitality and tourism sectors. By systematically evaluating current literature and suggesting a structured ML-CSA framework, it equips both researchers and industry professionals with the tools required to harness consumer sentiments effectively. The proposed areas for future research indicate that while significant advancements have been made, the field of consumer sentiment analysis continues to evolve, inviting further scholarly inquiry.