PSİKOLOJİK DANIŞMA VE REHBERLİKTE KONU MODELLEMESİ

Abstract

Bu makalede, metin madenciliği yöntemlerinden biri olan konu modellemesi analizi tanıtılarak bunun psikolojik danışma ve rehberlik alanında kullanımı ele alınmıştır. Konu modelleme, metin belgesinin temel anlamsal yapısının belirlenmesine ve yapılandırılmamış veri yapılarından anlamlı bilgiler çıkarmaya yarayan denetimsiz makine öğrenme algoritmalarının bir çerçevesidir. Bu doğrultuda bu makalede, psikolojik danışma ve rehberlik ve ilgili alanyazında yer bulan konu modellemesine dayalı araştırmalardan örnekler amaçlarına ve kullanılan veri kaynaklarına göre gruplandırılarak incelenmiştir. Ayrıca, bulguların analiz edilen veri setinin kalitesine bağlılığı, analizlerin bağlamı değerlendirmedeki eksiklikleri ve bulguların yorumlanmasındaki öznellik gibi sınırlılıklarının yanı sıra tarafsız ve adil bir temsili sağlayacak veri seti oluşturma, danışan transkriptlerinin kullanılması durumunda gizliliğin sağlanması ve bulgularda öne çıkan konuların isimlendirilmesi ve yorumlanmasında şeffaflık ve toplumsal yararlılık ilkelerinin göz önünde bulundurulması gibi etik hususlar ele alınmıştır. Son olarak, konu modellemesinin psikolojik danışma ve rehberlik alanında kurama, araştırmaya ve uygulamaya yönelik kullanımına dair öneriler sunulmuştur. ABSTRACT: This article introduces topic modeling analysis and its use in the field of counseling and guidance, one of the text mining methods. Topic modeling is a framework of unsupervised machine learning algorithms for determining the underlying semantic structure of a text document and extracting meaningful information from unstructured data structures. Thus, this article examines various topic modeling studies from psychiatry, psychology, and counseling fields by grouping them by purpose and data sources. The article also discusses limitations of topic modeling results, including dependence on data quality, challenges in contextual analysis and subjective interpretation, and ethical concerns such as ensuring unbiased dataset representation, confidentiality of client transcripts, and transparency and social utility in naming and interpreting themes. Finally, suggestions for the use of topic modeling in the field of counseling and guidance are also presented.

Keywords

• Veri madenciliği
• konu modellemesi
• makine öğrenmesi
• psikolojik danışma
• güncel araştırma yöntemleri

TOPIC MODELLING IN PSYCHOLOGICAL COUNSELING AND GUIDANCE

Abstract

This article introduces topic modeling analysis and its use in the field of counseling and guidance, one of the text mining methods. Topic modeling is a framework of unsupervised machine learning algorithms for determining the underlying semantic structure of a text document and extracting meaningful information from unstructured data structures. Thus, this article examines various topic modeling studies from psychiatry, psychology, and counseling fields by grouping them by purpose and data sources. The article also discusses limitations of topic modeling results, including dependence on data quality, challenges in contextual analysis and subjective interpretation, and ethical concerns such as ensuring unbiased dataset representation, confidentiality of client transcripts, and transparency and social utility in naming and interpreting themes. Finally, suggestions for the use of topic modeling in the field of counseling and guidance are also presented.

Keywords

• Text mining
• topic modelling
• machine learning
• psychological counseling
• contemporary research methodology

References

1. Atkins, D. C., Rubin, T. N., Steyvers, M., Doeden, M. A., Baucom, B. R., & Christensen, A. (2012). Topic models: A novel method for modeling couple and family text data. Journal of Family Psychology, 26, 816–827. https://doi.org/10.1037/a0029607
2. Atzil-Slonim, D., Juravski, D., Bar-Kalifa, E., Gilboa-Schechtman, E., Tuval-Mashiach, R., Shapira, N., & Goldberg, Y. (2021). Using topic models to identify clients' functioning levels and alliance ruptures in psychotherapy. Psychotherapy (Chicago, Ill.), 58(2), 324–339. https://doi.org/10.1037/pst0000362
3. Banks, G. C., Woznyj, H. M., Wesslen, R. S., & Ross, R. L. (2018). A review of best practice recommendations for text analysis in R (and a user-friendly app). Journal of Business and Psychology, 33(4), 445–459. https://doi.org/10.1007/s10869-017-9528-3
4. Balahadia, F. F., Fernando, M. C. G., & Juanatas, I. C. (2016). Teacher’s performance evaluation tool using opinion mining with sentiment analysis. In IEEE region symposium (TENSYMP) (pp. 95–98). https://doi.org/10.1109/TENCONSpring.2016.7519384
5. Baumer, E. P., Mimno, D., Guha, S., Quan, E., & Gay, G. K. (2017). Comparing grounded theory and topic modeling: Extreme divergence or unlikely convergence? Journal of the Association for Information Science and Technology, 68, 1397–1410. https://doi.org/10.1002/asi.23786
6. Buenano-Fernandez, D., Gonzalez, M., Gil, D., & Lujan-Mora, S. (2020). Text mining of open-ended questions in self-assessment of university teachers: An LDA topic modeling approach. IEEE Access, 8, 35318–35330. https://doi.org/10.1109/ACCESS.2020.2974983
7. Blei, D. M. (2012). Probabilistic topic models. Communications of the ACM, 55(4), 77-84. https://doi.org/10.1145/2133806.2133826
8. Blei, D. M., & Jordan, M. I. (2003, July). Modeling annotated data. In Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval (pp. 127-134).

9. Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent dirichlet allocation. Journal of machine Learning research, 3(Jan), 993-1022.
10. Blei, D., & Lafferty, J. (2009). Topic Models. In A. Srivastava & M. Sahami (Eds.), Text Mining: Classification, Clustering, and Applications (pp. 71-94). Boca Raton, FL: Chapman & Hall/CRC.