A Systematic Review of the Sentiment Analysis Models Used in Handling Polarity Shift

  • Millicent K. Murithi Computer Science Department, Murang’a University of Technology, Kenya
  • Aaron M. Oirere Computer Science Department, Murang’a University of Technology, Kenya
  • Rachael N. Ndung’u Information Technology Department, Murang’a University of Technology, Kenya

Abstract

Purpose – This comprehensive review aims to analyze sentiment analysis models, focusing on their effectiveness in managing polarity shifts (positive, neutral, and negative sentiments). The investigation delves into specific aspects, including feature selection/extraction techniques, data augmentation, input datasets, and evaluation metrics. The goal is to provide valuable insights for both theoretical understanding and practical applications, guiding advanced research.

Method – Following Kitchenham’s framework, the review conducts an exhaustive literature search, emphasizing entities embedded within sentiment analysis models. This methodological approach explores intricate challenges associated with polarity shifts, revealing opportunities for future research.



Results – Key findings highlight the efficacy of sentiment analysis models in handling polarity shifts. Recursive Feature Elimination emerges as the most effective wrapper-based feature selection technique, with Word2Vec standing out for word embeddings. Notably, negation is identified as a significant polarity shifter. The study also identifies common datasets, machine learning, and deep-learning models, emphasizing the effectiveness of hybrid models and ensembles.



Conclusion – This systematic review offers a comprehensive analysis of sentiment analysis models, providing insights into their status and key trends. The findings contribute to advancing the field, offering valuable guidance for researchers, practitioners, and developers working on polarity shift challenges, particularly in addressing implicit negation.



Recommendations – Future research should prioritize refining models addressing implicit negation, requiring empirical investigations to assess their effectiveness. Additionally, efforts should focus on developing standardized evaluation metrics to accurately capture the intricacies of polarity shifts, ensuring a comprehensive assessment of model performance. Implementing these recommendations will advance the state-of-the-art.



Research Implications – The review suggests practical and theoretical implications by highlighting effective models and their embedded entities. Recognition of explicit negation underscores the need for models capable of discerning and addressing negated sentiments. Practitioners are encouraged to adopt diverse strategies, and research opportunities lie in exploring implicit negation for ongoing innovation in sentiment analysis research.

Author Biographies

Millicent K. Murithi, Computer Science Department, Murang’a University of Technology, Kenya

Millicent Kathambi Murithi is a Tutorial Fellow at the Computer Science Department, Murang'a University of Technology, Kenya. She holds an MSc. Degree in Computer Systems from Jomo Kenyatta University of Science and Technology, Kenya. Her research interests include Machine Learning, software engineering, and Natural Language Processing.

Aaron M. Oirere, Computer Science Department, Murang’a University of Technology, Kenya

Aaron Mogeni Oirere is a Lecturer at the Department of Computer Science, Murang’a University of Technology, Kenya. He holds a Ph.D. degree in Computer Science from Dr. Babasaheb Ambedkar Marathwada University, Maharashtra, India. His research interests include Automatic Speech Recognition, Human-computer Interaction, Information Retrieval, Database Management Systems (DBMS), Data Analytics and Hardware & Networking.

Rachael N. Ndung’u, Information Technology Department, Murang’a University of Technology, Kenya

Rachael Njeri Ndung'u is a Lecturer at the Department of Information Technology, Murang’a University of Technology, Kenya. She holds a Ph.D. degree in Information Technology. Her research interests include Artificial Intelligence, Data Analytics ,and Blockchain.

Published
2024-02-26
How to Cite
MURITHI, Millicent K.; OIRERE, Aaron M.; NDUNG’U, Rachael N.. A Systematic Review of the Sentiment Analysis Models Used in Handling Polarity Shift. International Journal of Computing Sciences Research, [S.l.], v. 8, p. 2635-2676, feb. 2024. ISSN 2546-115X. Available at: <//stepacademic.net/ijcsr/article/view/479>. Date accessed: 12 dec. 2024.
Section
Articles