A DATA-CENTRIC STUDY OF ASPECT-BASED SENTIMENT ANALYSIS FOR SAFETY DISCOURSE IN TIKTOK TRAVEL CONTENT
DOI:
https://doi.org/10.35631/IJMOE.829075Keywords:
Aspect-Based Sentiment Analysis, Data-Centric AI, Safety Discourse, Social Media Mining, TikTok AnalyticsAbstract
Short-form social media platforms increasingly function as informal information systems through which safety perceptions are expressed and circulated. However, aspect-based sentiment analysis (ABSA) applied to safety discourse remains constrained by data sparsity, hierarchical label imbalance, and limited domain-specific resources. This study presents a data-centric investigation of ABSA for modelling safety-related discourse in TikTok comments associated with the #solotravel hashtag. A hierarchical annotation framework was developed comprising three primary safety aspects (physical/environmental, psychological/emotional, cultural/social), sixteen sub-aspects, and aspect-level sentiment polarity. Two datasets were constructed: a pilot dataset (402 comments) and an expanded dataset (2,362 comments), represented in multi-label exploded format. Classical baselines (Logistic Regression, SVM) and transformer architectures (DistilBERT, mBERT, XLM-R) were evaluated using five-fold cross-validation with macro-averaged metrics. Results demonstrate that annotation scale significantly influences model performance. At the pilot scale, classical models outperform transformer-based architectures. Following annotation expansion, transformer models surpass classical baselines for primary aspect classification, while classical models remain competitive for fine-grained subcategory and sentiment tasks. The results confirm that dataset scale, label distribution, and hierarchical design exert stronger influence on ABSA effectiveness than architectural complexity alone. The findings provide empirical validation for data-centric system design principles and offer methodological guidance for annotation-driven analytical studies in emerging digital discourse domains.
Downloads
References
Ahmad, W., Khan, H. U., Alarfaj, F., & Alreshoodi, M. (2025). Aspect-Based Sentiment Analysis: A Comprehensive Review and Open Research Challenges. IEEE Access, 13, 65138–65182. https://doi.org/10.1109/access.2025.3555744
Ali, T., Omar, B., & Soulaimane, K. (2022). Analyzing tourism reviews using an LDA topic-based sentiment analysis approach. MethodsX, 9, 101894. https://doi.org/10.1016/j.mex.2022.101894
Alotaibi, A., & Nadeem, F. (2025). An Unsupervised Integrated Framework for Arabic Aspect-Based Sentiment Analysis and Abstractive Text Summarization of Traffic Services Using Transformer Models. Smart Cities, 8(2). https://doi.org/10.3390/smartcities8020062
Aziz, K., Ji, D., Chakrabarti, P., Chakrabarti, T., Iqbal, M. S., & Abbasi, R. (2024). Unifying aspect-based sentiment analysis BERT and multi-layered graph convolutional networks for comprehensive sentiment dissection. Scientific Reports, 14, 14646. https://doi.org/10.1038/s41598-024-61886-7
Chauhan, A., Sharma, A., & Mohana, R. (2024). A Pre-Trained Model for Aspect-based Sentiment Analysis Task: Using Online Social Networking. In Procedia Computer Science (Vol. 233, pp. 35–44). Elsevier B.V. https://doi.org/10.1016/j.procs.2024.03.193
Chen, X., Xie, H., Tao, X., Wang, F. L., Zhang, D., & Dai, H.-N. (2025). A Computational Analysis of Aspect-based Sentiment Analysis Research Through Bibliometric Mapping and Topic Modeling. Journal of Big Data, 12(1), 40. https://doi.org/10.1186/s40537-025-01068-y
Chowdhury, S., Patel, P., Giridharan, V., & Ceccato, V. (2023). Formation of Fear and Adaptive Behavior in Young Ethnic Minority Women Riding Public Transport. Transportation Research Record. https://doi.org/10.1177/03611981231182712
Chu, M., Chen, Y., Yang, L., & Wang, J. (2022). Language interpretation in travel guidance platform: Text mining and sentiment analysis of TripAdvisor reviews. Frontiers in Psychology, 13. https://doi.org/10.3389/fpsyg.2022.1029945
Dai, W., Kong, W., Shang, T., Feng, J., Wu, J., & Qu, T. (2025). Guideline for Novel Fine‐Grained Sentiment Annotation and Data Curation: A Case Study. Expert Systems. https://doi.org/10.1111/exsy.70022
Drašković, D., & Milanović, S. (2025). Aspect-based sentiment analysis of user-generated content from a microblogging platform. Journal of Big Data, 12(1), 186. https://doi.org/10.1186/s40537-025-01244-0
Fei, H., Chua, T.-S., Li, C., Ji, D., Zhang, M., & Ren, Y. (2022). On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training. ACM Trans. Inf. Syst., 41(2), 50:1-50:32. https://doi.org/10.1145/3564281
Ghadban, S., Kamar, R., & Haidar, R. (2023). Decoding International Solo Women Travelers’ Experience: A Qualitative Analysis of User-generated Videos. Journal of Outdoor Recreation and Tourism, 44, 100648. https://doi.org/10.1016/j.jort.2023.100648
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), 296. https://doi.org/10.1007/s10462-024-10906-z
Huang, S., Wu, X., Wu, X., & Wang, K. (2023). Sentiment Analysis Algorithm Using Contrastive Learning and Adversarial Training for POI Recommendation. Social Network Analysis and Mining. https://link.springer.com/article/10.1007/s13278-023-01076-x
Ison, J., Forsdike, K., Henry, N., Hooker, L., & Taft, A. (2023). “You’re just constantly on alert”: Women and Gender-Diverse People’s Experiences of Sexual Violence on Public Transport. Journal of Interpersonal Violence, 38(21–22), 11617–11641. https://doi.org/10.1177/08862605231186123
Jang, H., Rempel, E., Roth, D., Carenini, G., & Janjua, N. Z. (2021). Tracking COVID-19 Discourse on Twitter in North America: Infodemiology Study Using Topic Modeling and Aspect-Based Sentiment Analysis. Journal of Medical Internet Research, 23(2), e25431. https://doi.org/10.2196/25431
Kandhro, I. A., Ali, F., Uddin, M., Kehar, A., & Manickam, S. (2024). Exploring aspect-based sentiment analysis: An in-depth review of current methods and prospects for advancement. In Knowledge and Information Systems (Vol. 66, Issue 7, pp. 3639–3669). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/s10115-024-02104-8
Li, H., Yu, B. X. B., Li, G., & Gao, H. (2023). Restaurant Survival Prediction Using Customer-generated Content: An Aspect-based Sentiment Analysis of Online Reviews. Tourism Management, 96, 104707. https://doi.org/10.1016/j.tourman.2022.104707
Liu, J., Tian, Y., & Song, Y. (2025). Balanced Training Data Augmentation for Aspect-Based Sentiment Analysis (arXiv:2507.09485). arXiv. https://doi.org/10.48550/arXiv.2507.09485
M. Abdelgwad, M., A Soliman, T. H., I.Taloba, A., & Farghaly, M. F. (2022). Arabic Aspect-based Sentiment Analysis Using Bidirectional GRU-based Models. Journal of King Saud University - Computer and Information Sciences, 34(9), 6652–6662. https://doi.org/10.1016/j.jksuci.2021.08.030
Mehra, P. (2023). Unexpected Surprise: Emotion Analysis and Aspect-based Sentiment Analysis (ABSA) of User-generated Comments to Study Behavioral Intentions of Tourists. Tourism Management Perspectives, 45, 101063. https://doi.org/10.1016/j.tmp.2022.101063
Motevalli, M. M., Sohrabi, M. K., & Yaghmaee, F. (2025). Aspect-based Sentiment Analysis: A Dual-task Learning Architecture Using Imbalanced Maximized-area Under the Curve Proximate Support Vector Machine and Reinforcement Learning. Information Sciences, 689, 121449. https://doi.org/10.1016/j.ins.2024.121449
Perwira, R. I., Purnamasari, D. I., Permadi, V. A., & Agusdin, R. P. (2025). Domain-Specific Fine-Tuning of IndoBERT for Aspect-Based Sentiment Analysis in Indonesian Travel User-Generated Content. Journal of Information Systems Engineering and Business Intelligence, 11(1), 30–40. https://doi.org/10.20473/jisebi.11.1.30-40
Pitanatri, P. D. S., Adnyani, N. W. G., Kartini, L. P., & Valeri, M. (2025). Travel Motivations, Preferences, and Characteristics of Women Solo Travelers in Bali. Journal of Applied Sciences in Travel and Hospitality, 8(1), Article 1. https://doi.org/10.31940/jasth.v8i1.63-78
Ramasamy, M., & Elangovan, M. (2024). Optimized Neural Attention Mechanism for Aspect-based Sentiment Analysis Framework with Optimal Polarity-based Weighted Features. Knowledge and Information Systems, 66, 2501–2535.
Selamat, N. S., Che Mustapha, J., & Jaafar, J. (2026). Mapping Gendered Safety in Solo Female Travel: A Scoping Review of Computational Approaches and Digital Discourse. International Journal for Studies on Children, Women, Elderly and Disabled, 26.
Siddiqua, A., Bindumathi, V., Raghu, G., & Vamsi Bhargav, Y. S. (2024). Aspect-based Sentiment Analysis (ABSA) using Machine Learning Algorithms. 2024 Third International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE), 1–6. https://doi.org/10.1109/ICDCECE60827.2024.10549140
Tao, J., & Fang, X. (2020). Toward Multi-label Sentiment Analysis: A Transfer Learning-based Approach. Journal of Big Data, 7(1), 1. https://doi.org/10.1186/s40537-019-0278-0
Wankhade, M., Kulkarni, C., & Rao, A. C. S. (2024). A survey on aspect base sentiment analysis methods and challenges. Applied Soft Computing, 167, 112249. https://doi.org/10.1016/j.asoc.2024.112249
Xu, C., Wang, M., Ren, Y., & Zhu, S. (2024). Enhancing Aspect-based Sentiment Analysis in Tourism Using Large Language Models and Positional Information (arXiv:2409.14997). arXiv. https://doi.org/10.48550/arXiv.2409.14997
Yang, Y., & Liu, F. (2025). Research on Aspect-based Sentiment Analysis of Homestay Online Comments Based on BERT-BiLSTM-Multi-Head Attention. International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2024), 13560, 264–269. https://doi.org/10.1117/12.3061617
Yin, S. (2024). The Current State and Challenges of Aspect-Based Sentiment Analysis. Applied and Computational Engineering, 114, 25–31. https://doi.org/10.54254/2755-2721/2024.18197
Zhang, W., Li, X., Deng, Y., Bing, L., & Lam, W. (2023). A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges. IEEE Transactions on Knowledge and Data Engineering, 35(11), 11019–11038. https://doi.org/10.1109/TKDE.2022.3230975
Zhu, L., Xu, M., Bao, Y., Xu, Y., & Kong, X. (2022). Deep Learning for Aspect-based Sentiment Analysis: A Review. PeerJ Computer Science. https://peerj.com/articles/cs-1044/
