An Aspect-Based Sentiment Classification Method Using the Pachinko Allocation Model
Received: 17 April 2025 | Revised: 7 May 2025, 19 May 2025, and 26 May 2025 | Accepted: 31 May 2025 | Online: 2 August 2025
Corresponding author: Gopisetty Rathnamma
Abstract
Sentiment analysis is based on extracting features from customer reviews using topic modeling and Latent Dirichlet Allocation (LDA) from large textual data to extract useful information. Different methods have been proposed to adapt LDA to short texts. This study uses a Pachinko Allocation Model (PAM)-based method to examine opinions and extract aspects related to product information, using data augmentation to improve model training. Feature extraction is performed using the TF-IGM and TF-IDF-ICSDF methods, and an opinion lexicon is used to extract sentiment. The experimental results show that the PAM method provides accurate results in extracting aspect sentiments. The proposed method was compared with existing models and evaluated on two datasets for sentiment classification of reviews, achieving better accuracy.
Keywords:
feature extraction, PAM, aspect-based sentiment analysis, topic modelingDownloads
References
J. Singh, G. Singh, and R. Singh, "Optimization of sentiment analysis using machine learning classifiers," Human-centric Computing and Information Sciences, vol. 7, no. 1, Dec. 2017, Art. no. 32. DOI: https://doi.org/10.1186/s13673-017-0116-3
M. Al-Smadi, O. Qawasmeh, M. Al-Ayyoub, Y. Jararweh, and B. Gupta, "Deep Recurrent neural network vs. support vector machine for aspect-based sentiment analysis of Arabic hotels’ reviews," Journal of Computational Science, vol. 27, pp. 386–393, Jul. 2018. DOI: https://doi.org/10.1016/j.jocs.2017.11.006
P. Kalarani and S. Selva Brunda, "Sentiment analysis by POS and joint sentiment topic features using SVM and ANN," Soft Computing, vol. 23, no. 16, pp. 7067–7079, Aug. 2019. DOI: https://doi.org/10.1007/s00500-018-3349-9
N. C. Hellwig, J. Fehle, and C. Wolff, "Exploring large language models for the generation of synthetic training samples for aspect-based sentiment analysis in low resource settings," Expert Systems with Applications, vol. 261, Feb. 2025, Art. no. 125514. DOI: https://doi.org/10.1016/j.eswa.2024.125514
W. Maharani, D. H. Widyantoro, and M. L. Khodra, "Aspect Extraction in Customer Reviews Using Syntactic Pattern," Procedia Computer Science, vol. 59, pp. 244–253, 2015. DOI: https://doi.org/10.1016/j.procs.2015.07.545
C. Liao, C. Feng, S. Yang, and H. Huang, "Topic-related Chinese message sentiment analysis," Neurocomputing, vol. 210, pp. 237–246, Oct. 2016. DOI: https://doi.org/10.1016/j.neucom.2016.01.110
S. M. Rezaeinia, R. Rahmani, A. Ghodsi, and H. Veisi, "Sentiment analysis based on improved pre-trained word embeddings," Expert Systems with Applications, vol. 117, pp. 139–147, Mar. 2019. DOI: https://doi.org/10.1016/j.eswa.2018.08.044
M. E. Mowlaei, M. Saniee Abadeh, and H. Keshavarz, "Aspect-based sentiment analysis using adaptive aspect-based lexicons," Expert Systems with Applications, vol. 148, Jun. 2020, Art. no. 113234. DOI: https://doi.org/10.1016/j.eswa.2020.113234
M. Hu and B. Liu, "Mining and summarizing customer reviews," in Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining, May 2004, pp. 168–177. DOI: https://doi.org/10.1145/1014052.1014073
T. Sokhin and N. Butakov, "Semi-automatic sentiment analysis based on topic modeling," Procedia Computer Science, vol. 136, pp. 284–292, 2018. DOI: https://doi.org/10.1016/j.procs.2018.08.286
M. Zaheer, A. Ahmed, and A. J. Smola, "Latent LSTM Allocation: Joint Clustering and Non-Linear Dynamic Modeling of Sequence Data," in Proceedings of the 34th International Conference on Machine Learning, Jul. 2017, pp. 3967–3976.
Y. Jo, L. Lee, and S. Palaskar, "Combining LSTM and Latent Topic Modeling for Mortality Prediction." arXiv, 2017.
P. Jansson and S. Liu, "Topic modelling enriched LSTM models for the detection of novel and emerging named entities from social media," in 2017 IEEE International Conference on Big Data (Big Data), Boston, MA, Dec. 2017, pp. 4329–4336. DOI: https://doi.org/10.1109/BigData.2017.8258462
G. Pergola, L. Gui, and Y. He, "TDAM: A topic-dependent attention model for sentiment analysis," Information Processing & Management, vol. 56, no. 6, Nov. 2019, Art. no. 102084. DOI: https://doi.org/10.1016/j.ipm.2019.102084
M. A. Kausar, S. O. Fageeri, and A. Soosaimanickam, "Sentiment Classification based on Machine Learning Approaches in Amazon Product Reviews," Engineering, Technology & Applied Science Research, vol. 13, no. 3, pp. 10849–10855, Jun. 2023. DOI: https://doi.org/10.48084/etasr.5854
W. Li and A. McCallum, "Pachinko Allocation: Scalable Mixture Models of Topic Correlations," Journal of Machine Learning Research, 2008.
S. Baccianella, A. Esuli, and F. Sebastiani, "SentiWordNet 3.0: An Enhanced Lexical Resource for Sentiment Analysis and Opinion Mining," in Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10), Valletta, Malta, Feb. 2010.
"515K Hotel Reviews Data in Europe - Skyhighes Technologies," Jan. 16, 2025. https://skyhighes.in/courses/data-visualization-projects/lesson/515k-hotel-reviews-data-in-europe/.
"Download Amazon Review Dataset Of Mobile Phones," DataStock. https://datastock.shop/download-amazon-mobile-phone-reviews-dataset/.
T. Liesting, F. Frasincar, and M. M. Truşcă, "Data augmentation in a hybrid approach for aspect-based sentiment analysis," in Proceedings of the 36th Annual ACM Symposium on Applied Computing, Dec. 2021, pp. 828–835. DOI: https://doi.org/10.1145/3412841.3441958
Z. Jiang, B. Gao, Y. He, Y. Han, P. Doyle, and Q. Zhu, "Text Classification Using Novel Term Weighting Scheme-Based Improved TF-IDF for Internet Media Reports," Mathematical Problems in Engineering, vol. 2021, pp. 1–30, Mar. 2021. DOI: https://doi.org/10.1155/2021/6619088
K. Chen, Z. Zhang, J. Long, and H. Zhang, "Turning from TF-IDF to TF-IGM for term weighting in text classification," Expert Systems with Applications, vol. 66, pp. 245–260, Dec. 2016. DOI: https://doi.org/10.1016/j.eswa.2016.09.009
P. Asthana, M. Barnwal, A. Yadav, M. Aggrawal, and M. Goel, "VADER: A Lightweight and Effective Approach for Sentiment Analysis," in 2024 2nd International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT), Faridabad, India, Nov. 2024, pp. 687–692. DOI: https://doi.org/10.1109/ICAICCIT64383.2024.10912371
K. Tayal, A. Mehta, J. Kamboj, and S. Susan, "Fuzzy Aggregation of Polarity Scores for Unsupervised Sentiment Analysis Using AFINN, VADER and TextBlob," in Bio-Inspired Computing, 2025, pp. 47–54. DOI: https://doi.org/10.1007/978-3-031-78943-4_6
Downloads
How to Cite
License
Copyright (c) 2025 Yojitha Chilukuri, T. Jhansi Rani, N. Lakshmipathi Anantha, Gopisetty Rathnamma, Ulligaddala Srinivasarao, P. Sowjanya, Nemala Jayasri, Rakesh Kumar Donthi, B. Krishna Chaitanya, M. Ramesh
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
