Gigalyze: Aspect-Based Sentiment Analysis of Gig Economy Platform Services Using Support Vector Machines

The expansion of digital freelancing has increased the volume of user feedback associated with gig economy platforms, making manual interpretation slow and inconsistent. This paper presents Gigalyze, a web-based aspect-based sentiment analysis system for Google Play Store reviews of Fiverr, Freelancer, and Upwork. The dataset contains 30,000 English-language reviews, comprising 10,000 reviews per platform, collected for the Malaysian market between 2022 and 2025. Reviews were cleaned, spell-corrected, normalised, lemmatised, and represented using term frequency-inverse document frequency features. Non-negative matrix factorisation supported the derivation of four platform-service aspects: User Experience, App Performance and Functionality, Account and Support Issues, and Payment and Earnings. VADER compound scores supplied initial positive, neutral, and negative sentiment labels. Separate linear Support Vector Machine classifiers were developed for sentiment and aspect prediction, while the Synthetic Minority Over-sampling Technique was applied to the training data to reduce class imbalance. After balancing, sentiment accuracy reached 83.74%, neutral recall increased from 0.26 to 0.49, and macro F1-score increased from 0.68 to 0.73. Aspect accuracy reached 88.52%, with User Experience recall improving from 0.86 to 0.88. All 14 functional test cases passed. These results demonstrate the feasibility of interpretable machine-learning analytics for gig-platform reviews while also highlighting limitations stemming from automatically generated labels, overlapping aspect vocabularies, and subtle emotional expressions.

Artificial Intelligence, Information Science, MIS (Management Information System)

1. Abdelrazek, A., Eid, Y., Gawish, E., Medhat, W., & Hassan, A. (2023). Topic modeling algorithms and applications: A survey. Information Systems, 112, 102131. https://doi.org/10.1016/j.is.2022.102131 [Google Scholar] [Crossref]

2. Ali, S., Wang, G., & Riaz, S. (2020). Aspect based sentiment analysis of ridesharing platform reviews for Kansei engineering. IEEE Access, 8, 173186-173196. https://doi.org/10.1109/ACCESS.2020.3025823 [Google Scholar] [Crossref]

3. Brauwers, G., & Frasincar, F. (2022). A survey on aspect-based sentiment classification. ACM Computing Surveys, 55(4). https://doi.org/10.1145/3503044 [Google Scholar] [Crossref]

4. Budaya, I. G. B. A., & Suniantara, I. K. P. (2024). Comparison of sentiment analysis algorithms with SMOTE oversampling and TF-IDF implementation on Google Reviews for public health centers. MALCOM, 4(3), 1077-1086. https://doi.org/10.57152/malcom.v4i3.1459 [Google Scholar] [Crossref]

5. Cervantes, J., Garcia-Lamont, F., Rodriguez-Mazahua, L., & Lopez, A. (2020). A comprehensive survey on support vector machine classification: Applications, challenges and trends. Neurocomputing, 408, 189-215. https://doi.org/10.1016/j.neucom.2019.10.118 [Google Scholar] [Crossref]

6. Dedema, M., & Rosenbaum, H. (2024). Socio-technical issues in the platform-mediated gig economy: A systematic literature review. Journal of the Association for Information Science and Technology, 75(3), 344-374. https://doi.org/10.1002/asi.24868 [Google Scholar] [Crossref]

7. Green, D. D., McCann, J., Vu, T., Lopez, N., & Ouattara, S. (2018a). Gig economy and the future of work: A Fiverr.com case study. Management and Economics Research Journal, 4(2), 281. https://doi.org/10.18639/MERJ.2018.04.734348 [Google Scholar] [Crossref]

8. Green, D. D., Walker, C., Alabulththim, A., Smith, D., & Phillips, M. (2018b). Fueling the gig economy: A case study evaluation of Upwork.com. Management and Economics Research Journal, 4, 104. https://doi.org/10.18639/MERJ.2018.04.523634 [Google Scholar] [Crossref]

9. Green, D. D., Polk, X., O'Donnell, H., Doughty, K., Carr, M., & Costa-Cargill, D. (2021). The gig economy: A case study analysis of Freelancer.com. Management and Economics Research Journal, 7(2), 1-6. https://doi.org/10.18639/merj.2021.1413412 [Google Scholar] [Crossref]

10. Harun, N., Ali, N. M., & Khan, N. L. M. A. (2020). An experimental measure of Malaysia's gig workers using labour force survey. Statistical Journal of the IAOS, 36(4), 969-977. https://doi.org/10.3233/SJI-200749 [Google Scholar] [Crossref]

11. Hua, Y. C., Denny, P., Wicker, J., & Taskova, K. (2024). A systematic review of aspect-based sentiment analysis: Domains, methods, and trends. Artificial Intelligence Review, 57(11). https://doi.org/10.1007/s10462-024-10906-z [Google Scholar] [Crossref]

12. Indrawan, N. A., Sucahyo, Y. G., Ruldeviyani, Y., & Gandhi, A. (2020). What users want for gig economy platforms: Sentiment analysis approach. 2020 6th International Conference on Science in Information Technology, 68-73. https://doi.org/10.1109/ICSITech49800.2020.9392060 [Google Scholar] [Crossref]

13. Lee, D. D., & Seung, H. S. (2001). Algorithms for non-negative matrix factorization. Advances in Neural Information Processing Systems, 13. [Google Scholar] [Crossref]

14. Muhyi, S. N. A., Omar, S. I., & Adnan, S. F. (2023). The drivers force the gig workers into gig economy: The case of Malaysia. Journal of Business and Social Development, 11(1), 1-12. https://doi.org/10.46754/jbsd.2023.03.001 [Google Scholar] [Crossref]

15. Mustakim, H., & Priyanta, S. (2022). Aspect-based sentiment analysis of KAI Access reviews using NBC and SVM. IJCCS, 16(2), 113. https://doi.org/10.22146/ijccs.68903 [Google Scholar] [Crossref]

16. Nurul Hidayati, S., Hamami, F., & Fa'rifah, R. Y. (2023). Aspect-based sentiment analysis on FLIP application reviews using Support Vector Machine. Journal of Informatics and Telecommunication Engineering, 7(1), 183-197. https://doi.org/10.31289/jite.v7i1.9768 [Google Scholar] [Crossref]

17. Pilatti, G. R., Pinheiro, F. L., & Montini, A. A. (2024). Systematic literature review on gig economy: Power dynamics, worker autonomy, and the role of social networks. Administrative Sciences, 14(10), 267. https://doi.org/10.3390/admsci14100267 [Google Scholar] [Crossref]