Dirichlet Multinomial Modelling Approaches in Analyzing Anxiety Therapy Messages
DOI:
https://doi.org/10.24191/jikm.v15i1.4541Keywords:
topic modelling, text analysis, DMM, anxiety topicAbstract
Despite the effectiveness of anxiety therapy through text messages, limited research was found to analyse the topics included in the therapy session. It is also unclear of which topic modelling approaches is the best in extracting anxiety therapy topics from text messages. Thus, this study aims to compare the performance of four topic modelling methods, namely Latent Feature Di-richlet Multinomial Mixture (LFDMM), Gibbs Sampling Dirichlet Multinomi-al Mixture, Generalized Polya-urn Dirichlet Multinomial Mixture and Pois-son-based Dirichlet Multinomial Mixture Model on 28 text messages of anxi-ety-therapy. Four combinations of parameter settings were applied in the ex-periments to compare and decide the most suitable ones for future analysis. The performance of the topic modelling was evaluated using classification accuracy, clustering, and coherence scores. The findings shows that LFDMM has the best accuracy (34.10%) and clustering scores (0.5000, 0.4808) with combinations of hyperparameters α = 0.1 and β = 0.01 to infer more relevant topics.
References
Aguilera, A., Hernandez-Ramos, R., Haro-Ramos, A. Y., Boone, C. E., Luo, T. C., Jing, X., Chakraborty, B., Karr, C., Darrow, S., & Figueroa, C. A. (2021). A Text Messaging Intervention ( StayWell at Home ) to Counteract Depression and Anxiety During COVID-19 Social Distancing : Pre-Post Study. JMIR Mental Health, 8(11). https://doi.org/10.2196/25298
Agyapong, V. I. O., Hrabok, M., Vuong, W., Gusnowski, A., Shalaby, R., Surood, S., Greenshaw, A. J., Aulakh, A., Abba-Aji, A., & Singh, M. (2020). Implementation and evaluation of a text message-based addiction counseling program (text4hope-addiction support): Protocol for a questionnaire study. JMIR Research Protocols, 9(11). https://doi.org/10.2196/22047
Agyapong, V. I. O., Juhás, M., Ohinmaa, A., Omeje, J., Mrklas, K., Suen, V. Y. M., Dursun, S. M., & Greenshaw, A. J. (2017). Randomized controlled pilot trial of supportive text messages for patients with depression. BMC Psychiatry, 17(1), 1–10. https://doi.org/10.1186/s12888-017-1448-2
Agyapong, V. I. O., Mrklas, K., Juhás, M., Omeje, J., Ohinmaa, A., Dursun, S. M., & Greenshaw, A. J. (2016). Cross-sectional survey evaluating Text4Mood: Mobile health program to reduce psychological treatment gap in mental healthcare in Alberta through daily supportive text messages. BMC Psychiatry, 16(1), 1–12. https://doi.org/10.1186/s12888-016-1104-2
Alfonsson, S., Englund, J., & Parling, T. (2019). Tailored text message prompts to increase therapy homework adherence: A single-case randomised controlled study. Behaviour Change, 36(3), 180–191. https://doi.org/10.1017/bec.2019.10
Anstiss, D., & Davies, A. (2015). “Reach Out, Rise Up”: The efficacy of text messaging in an intervention package for anxiety and depression severity in young people. Children and Youth Services Review, 58, 99–103. https://doi.org/10.1016/j.childyouth.2015.09.011
Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent Dirichlet allocation. Journal of Machine Learning Research, 3(4–5), 993–1022. https://doi.org/10.1016/b978-0-12-411519-4.00006-9
Chandran, S., Mathur, S., & Rao, K. M. (2019). Media and the role of digital psychiatry in mental health. Digital Psychiatry, 2(1), 34–44. https://doi.org/10.1080/2575517x.2019.1651625
Clough, B. A., & Casey, L. M. (2018). Will patients accept daily SMS as a communication to support adherence to mental health treatment? Daily SMS: Acceptance, feasibility, & satisfaction. International Journal of Cyber Behavior, Psychology and Learning, 8(3), 24–35. https://doi.org/10.4018/IJCBPL.2018070103
Fairie, P., Zhang, Z., D’Souza, A. G., Walsh, T., Quan, H., & Santana, M. J. (2021). Categorising patient concerns using natural language processing techniques. BMJ Health and Care Informatics, 28(1), 1–9. https://doi.org/10.1136/bmjhci-2020-100274
Fitzpatrick, K. K., Darcy, A., & Vierhile, M. (2017). Delivering cognitive behavior therapy to young adults with symptoms of depression and anxiety using a fully automated conversational agent (Woebot): A randomized controlled trial. JMIR Mental Health, 4(2), 1–11. https://doi.org/10.2196/mental.7785
Furber, G., Jones, G. M., Healey, D., & Bidargaddi, N. (2014). A comparison between phone-based psychotherapy with and without text messaging support in between sessions for crisis patients. Journal of Medical Internet Research, 16(10), e219. https://doi.org/10.2196/jmir.3096
García, Y., Ferrás, C., Rocha, Á., & Aguilera, A. (2019). Exploratory Study of Psychosocial Therapies with Text Messages to Mobile Phones in Groups of Vulnerable Immigrant Women. Journal of Medical Systems, 43(8). https://doi.org/10.1007/s10916-019-1393-3
Gupta, R. K., Agarwalla, R., Naik, B. H., Evuri, J. R., Thapa, A., & Singh, T. D. (2022). Prediction of research trends using LDA based topic modeling. Global Transitions Proceedings, 3(1), 298–304. https://doi.org/10.1016/j.gltp.2022.03.015
Kachouie, N. N., & Shutaywi, M. (2020). Weighted mutual information for aggregated kernel clustering. Entropy, 22(3), 1–15. https://doi.org/10.3390/e22030351
Kao, S. W., & Luarn, P. (2020). Topic modeling analysis of social enterprises: Twitter evidence. Sustainability (Switzerland), 12(8), 1–20. https://doi.org/10.3390/SU12083419
Li, C., Duan, Y., Wang, H., Zhang, Z., Sun, A., & Ma, Z. (2017). Enhancing topic modeling for short texts with auxiliary word embeddings. ACM Transactions on Information Systems, 36(2), 1–30. https://doi.org/10.1145/3091108
Li, C., Wang, H., Zhang, Z., Sun, A., & Ma, Z. (2016). Topic modeling for short texts with auxiliary word embeddings. SIGIR 2016 - Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, 165–174. https://doi.org/10.1145/2911451.2911499
Murshed, B. A. H., Mallappa, S., Abawajy, J., Saif, M. A. N., Al-ariki, H. D. E., & Abdulwahab, H. M. (2022). Short text topic modelling approaches in the context of big data: taxonomy, survey, and analysis. Artificial Intelligence Review. https://doi.org/10.1007/s10462-022-10254-w
Nguyen, D. Q., Billingsley, R., Du, L., & Johnson, M. (2015). Improving Topic Models with Latent Feature Word Representations. Transactions of the Association for Computational Linguistics, 3, 598–599. https://doi.org/10.1162/tacl_a_00245
Qiang, J., Qian, Z., Li, Y., Yuan, Y., & Wu, X. (2019). Short text topic modeling techniques, applications, and performance: A survey. Journal of Latex Class Files, 14(8), 1–17. https://doi.org/10.1109/tkde.2020.2992485
Ritvo, P., Knyahnytska, Y., Pirbaglou, M., Wang, W., Tomlinson, G., Zhao, H., Linklater, R., Bai, S., Kirk, M., Katz, J., Harber, L., & Daskalakis, Z. (2021). Online mindfulness-based cognitive behavioral therapy intervention for youth with major depressive disorders: Randomized controlled trial. Journal of Medical Internet Research, 23(3), 1–11. https://doi.org/10.2196/24380
Schneider, J., & Vlachos, M. (2018). Topic modeling based on keywords and context. Proceedings of the 2018 SIAM International Conference on Data Mining, May, 369–377. https://doi.org/10.1137/1.9781611975321.42
Voskergian, D., Bakir-Gungor, B., & Yousef, M. (2023). TextNetTopics Pro, a topic model-based text classification for short text by integration of semantic and document-topic distribution information. Frontiers in Genetics, 14(October), 1–23. https://doi.org/10.3389/fgene.2023.1243874
Weisser, C., Gerloff, C., Thielmann, A., Python, A., Reuter, A., Kneib, T., & Säfken, B. (2023). Pseudo-document simulation for comparing LDA, GSDMM and GPM topic models on short and sparse text using Twitter data. Computational Statistics, 38(2), 647–674. https://doi.org/10.1007/s00180-022-01246-z
Xie, R., Chu, S. K. W., Chiu, D. K. W., & Wang, Y. (2021). Exploring Public Response to COVID-19 on Weibo with LDA Topic Modeling and Sentiment Analysis. Data and Information Management, 5(1), 86–99. https://doi.org/10.2478/dim-2020-0023
Yan, X., Guo, J., Lan, Y., & Cheng, X. (2013). A biterm topic model for short texts. WWW 2013 - Proceedings of the 22nd International Conference on World Wide Web, May, 1445–1455. https://doi.org/10.1145/2488388.2488514
Yin, J., & Wang, J. (2014). A Dirichlet multinomial mixture model-based approach for short text clustering. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 233–242. https://doi.org/10.1145/2623330.2623715
Zuo, Y., Wu, J., Xhang, H., Lin, H., Wang, F., Xu, K., & Xiong, H. (2016). Topic Modeling of Short Texts: A Pseudo-Document View. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2105–2114. https://doi.org/10.1109/TKDE.2021.3073195
Zuo, Y., Zhao, J., & Xu, K. (2016). Word network topic model: a simple but general solution for short and imbalanced texts. Knowledge and Information Systems, 48(2), 379–398. https://doi.org/10.1007/s10115-015-0882-z
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Teh Faradilla Abdul Rahman, Norshita Mat Nayan, Nurhilyana Anuar, Aminatul Solehah Idris
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright of articles that appear in the journal belongs exclusively to Faculty of Information Science, Universiti Teknologi MARA (Publisher). This copyright covers the rights to reproduce the article, including reprints, electronic reproductions or any other reproductions of similar nature.
