Araştırma Makalesi
BibTex RIS Kaynak Göster

TRANSFORMER TABANLI DUYGU SINIFLANDIRMASI İLE SOSYAL MEDYADA RUH SAĞLIĞINA İLİŞKİN TÜRKÇE YORUMLARIN ANALİZİ

Yıl 2025, Cilt: 28 Sayı: 3, 1499 - 1511, 03.09.2025

Erol Kına

https://doi.org/10.17780/ksujes.1694291

Öz

Instagram platformunda paylaşılan Türkçe yorumlar üzerinden ruh sağlığına yönelik duygusal tepkilerin makine öğrenimi algoritmaları ile incelenmesini amaçlayan bu çalışmada, XLM-RoBERTa-Large, BERTurk ve Electra-Turkish gibi güncel ve güçlü Transformer tabanlı modeller kullanılarak çok kategorili duygu sınıflandırması gerçekleştirilmiştir. Belirlenen zaman diliminde toplanan veriler, beş farklı duygu kategorisine ayrılarak etiketlenmiş ve modellerin doğruluk ve F1-Skoru gibi ölçütler üzerinden performansları karşılaştırılmıştır. Analiz sonuçlarına göre, XLM-RoBERTa-Large modeli %92 doğruluk ve %90.5 F1-skoru ile en yüksek performansı sergilemiştir. Tüm modeller bazında yapılan değerlendirmede, en yüksek doğruluk ve F1-skoru değerlerinin Şükran ve Aşk/Hayranlık kategorilerinde elde edildiği görülmüştür. Öte yandan, her üç modelde de en düşük sınıflandırma performansının Üzüntü kategorisinde olduğu belirlenmiştir. Özellikle XLM-RoBERTa-Large modeli, "Şükran" sınıfında %94 doğruluk ve %94.5 F1-skoru ile en başarılı sonuçları sağlamıştır. Anlam olarak yakın duyguların varlığı, modellerin duygu ayrımındaki performansını olumsuz yönde etkilemiştir. Çalışmanın bulguları, sosyal medya verilerinin ruh sağlığına ilişkin duygusal eğilimlerin analizinde değerli bir kaynak olabileceğini göstermiştir.

Anahtar Kelimeler

duygu sınıflandırması makine öğrenmesi ruh sağlığı transformers model

Kaynakça

  • Avcı, İ., & Koca, M. (2024). Intelligent transportation system technologies, challenges and security. Applied Sciences, 14(11), 4646. https://doi.org/10.3390/app14114646.
  • Benrouba, F., & Boudour, R. (2023). Emotional sentiment analysis of social media content for mental health safety. Social Network Analysis and Mining, 13(1), 17. https://doi.org/10.1007/s13278-022-01000-9.
  • Betton, V., Borschmann, R., Docherty, M., Coleman, S., Brown, M., & Henderson, C. (2015). The role of social media in reducing stigma and discrimination. The British Journal of Psychiatry, 206(6), 443-444. https://doi: 10.1192/bjp.bp.114.152835.
  • Conway, M., & O’Connor, D. (2016). Social media, big data, and mental health: current advances and ethical implications. Current opinion in psychology, 9, 77-82. https://doi.org/10.1016/j.copsyc.2016.01.004.
  • Çakıcı, Ş., Karaduman, D., Çırlan, M. A., & Hürriyetoğlu, A. (2024). A Cross-Validation Study of Turkish Sentiment Analysis Datasets and Tools. arXiv preprint arXiv:2412.05964. https://doi.org/10.48550/arXiv.2412.05964.
  • Digital 2024: Global Overview Report. (2024). https://datareportal.com/reports/digital-2024-global-overview-report accessed 29.04.2025
  • Ekman, P. (1999). Basic emotions. Handbook of cognition and emotion. Sussex, U.K. John Wiley & Sons, Ltd.
  • Ghahramani, A., de Courten, M., & Prokofieva, M. (2022). The potential of social media in health promotion beyond creating awareness: an integrative review. BMC public health, 22(1), 2402. https://doi.org/10.186/s12889-022-14885-0.
  • Gronholm, P. C., & Thornicroft, G. (2022). Impact of celebrity disclosure on mental health-related stigma. Epidemiology and psychiatric sciences, 31, e62. https://doi.org/10.1017/S2045796022000488.
  • Hadikhah Mozhdehi, M., & Eftekhari Moghadam, A. (2023). Textual emotion detection utilizing a transfer learning approach. The Journal of Supercomputing, 79(12), 13075-13089. https://doi.org/10.1007/s11227-023-05168-5.
  • Hajizadeh, A., Amini, H., Heydari, M., & Rajabi, F. (2024). How to combat stigma surrounding mental health disorders: a scoping review of the experiences of different stakeholders. BMC psychiatry, 24(1), 782. https://doi.org/10.1186/s12888-024-06220-1.
  • Herrera-Peco, I., Fernández-Quijano, I., & Ruiz-Núñez, C. (2023). The role of social media as a resource for mental health care. European journal of investigation in health, psychology and education, 13(6), 1026-1028. https://doi.org/10.3390/ejihpe13060078.
  • Hyman, S. E. (2023). The biology of mental disorders: Progress at last. Dædalus, 152(4), 186-211. https://doi.org/10.1162/daed_a_02038.
  • İş, H., & Tuncer, T. (2021). A Profile Analysis of User Interaction in Social Media Using Deep Learning. Traitement du signal, 38(1). https://doi.org/10.18280/ts.380101.
  • İş, H., & Tuncer, T. (2019). Interaction-based behavioral analysis of twitter social network accounts. Applied Sciences, 9(20), 4448. https://doi.org/10.3390/app9204448.
  • Kina, E. (2025). TLEABLCNN: Brain and Alzheimer’s disease detection using attention-based explainable deep learning and SMOTE using imbalanced brain MRI. IEEE Access, 13, 27670–27683. https://doi.org/10.1109/ACCESS.2025.3539550.
  • Kına, E., & Biçek, E. (2024). Machine Learning Approach for Emotion Identification and Classification in Bitcoin Sentiment Analysis. Yüzüncü Yıl Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 29(3), 913-926. https://doi.org/10.53433/yyufbed.1532649.
  • Kına, E., & Biçek, E. (2023). Tweetlerin duygu analizi için hibrit bir yaklaşım. Doğu Fen Bilimleri Dergisi, 6(1), 57-68. https://doi.org/10.57244/dfbd.1314901.
  • Koca, M., & Avcı, İ. (2024a). Enhancing Network Security: A Comprehensive Analysis of Intrusion Detection Systems. Yüzüncü Yıl Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 29(3), 927–938. https://doi.org/10.53433/yyufbed.1545033.
  • Koca, M., & Avcı, İ. (2024b). Optimization Planning Techniques with Meta-Heuristic Algorithms in IoT: Performance and QoS Evaluation. Sakarya University Journal of Computer and Information Sciences, 7(2), 173-18. https://doi.org/10.35377/saucis...1452049.
  • Mental health of adolescents. (2021). https://www.who.int/news-room/fact-sheets/detail/adolescent-mental-health (accessed 01.01.2025)
  • Mujahid, M., Lee, E., Rustam, F., Washington, P. B., Ullah, S., Reshi, A. A., & Ashraf, I. (2021). Sentiment analysis and topic modeling on tweets about online education during COVID-19. Applied Sciences, 11(18), 8438. https://doi.org/10.3390/app11188438.
  • Nguyen, V. C., Birnbaum, M., & De Choudhury, M. (2023). Understanding and Mitigating Mental Health Misinformation on Video Sharing Platforms. arXiv preprint arXiv:2304.07417. https://doi.org/10.48550/arXiv.2304.07417.
  • Pacheco, J. P., Giacomin, H. T., Tam, W. W., Ribeiro, T. B., Arab, C., Bezerra, I. M., & Pinasco, G. C. (2017). Mental health problems among medical students in Brazil: a systematic review and meta-analysis. Brazilian Journal of Psychiatry, 39, 369–378. https://doi.org/10.1590/1516-4446-2017-2223.
  • P Plutchik, R. (2003). Emotions and life: Perspectives from psychology, biology, and evolution. American Psychological Association.
  • Prizeman, K., Weinstein, N., & McCabe, C. (2023). Effects of mental health stigma on loneliness, social isolation, and relationships in young people with depression symptoms. BMC psychiatry, 23(1), 527. https://doi.org/10.1186/s12888-023-04991-7.
  • Skaik, R., & Inkpen, D. (2020). Using social media for mental health surveillance: a review. ACM Computing Surveys (CSUR), 53(6), 1-31. https://doi.org/10.1145/3422824.
  • Suman, S. K., Shalu, H., Agrawal, L. A., Agrawal, A., & Kadiwala, J. (2020). A novel sentiment analysis engine for preliminary depression status estimation on social media. arXiv preprint arXiv:2011.14280. https://doi.org/10.48550/arXiv.2011.14280.
  • Zollo, F., Baronchelli, A., Betsch, C., Delmastro, M., & Quattrociocchi, W. (2024). Understanding the complex links between social media and health behaviour. BMJ, 385:e075645. https://doi.org/10.1136/bmj-2023-075645.

ANALYSIS OF TURKISH COMMENTS ON MENTAL HEALTH IN SOCIAL MEDIA THROUGH TRANSFORMER-BASED EMOTION CLASSIFICATION

Yıl 2025, Cilt: 28 Sayı: 3, 1499 - 1511, 03.09.2025

Erol Kına

https://doi.org/10.17780/ksujes.1694291

Öz

In this study, which aims to examine emotional reactions towards mental health through Turkish comments shared on the Instagram platform using machine learning algorithms, multi-category sentiment classification was performed utilizing current and powerful Transformer-based models such as XLM-RoBERTa-Large, BERTurk, and Electra-Turkish. The dataset, collected over a specified time period, was labeled into five distinct sentiment categories. The models’ performances were evaluated and compared based on key metrics, including accuracy and F1-Score. According to the analysis results, the XLM-RoBERTa-Large model achieved the best performance with 92% accuracy and a 90.5% F1-Score. the XLM-RoBERTa-Large model provided the best results in the “Gratitude” category with 94% accuracy and 94.5% F1-score. In the evaluation of all models, it was observed that the highest accuracy and F1- Conversely, the Sadness category yielded the lowest classification performance across all models. The close semantic proximity between certain emotional categories was found to negatively impact model performance. The study’s findings indicate that social media data can serve as a valuable resource for analyzing emotional tendencies related to mental health.

Anahtar Kelimeler

emotion classification machine learning transformers model mental health

Kaynakça

  • Avcı, İ., & Koca, M. (2024). Intelligent transportation system technologies, challenges and security. Applied Sciences, 14(11), 4646. https://doi.org/10.3390/app14114646.
  • Benrouba, F., & Boudour, R. (2023). Emotional sentiment analysis of social media content for mental health safety. Social Network Analysis and Mining, 13(1), 17. https://doi.org/10.1007/s13278-022-01000-9.
  • Betton, V., Borschmann, R., Docherty, M., Coleman, S., Brown, M., & Henderson, C. (2015). The role of social media in reducing stigma and discrimination. The British Journal of Psychiatry, 206(6), 443-444. https://doi: 10.1192/bjp.bp.114.152835.
  • Conway, M., & O’Connor, D. (2016). Social media, big data, and mental health: current advances and ethical implications. Current opinion in psychology, 9, 77-82. https://doi.org/10.1016/j.copsyc.2016.01.004.
  • Çakıcı, Ş., Karaduman, D., Çırlan, M. A., & Hürriyetoğlu, A. (2024). A Cross-Validation Study of Turkish Sentiment Analysis Datasets and Tools. arXiv preprint arXiv:2412.05964. https://doi.org/10.48550/arXiv.2412.05964.
  • Digital 2024: Global Overview Report. (2024). https://datareportal.com/reports/digital-2024-global-overview-report accessed 29.04.2025
  • Ekman, P. (1999). Basic emotions. Handbook of cognition and emotion. Sussex, U.K. John Wiley & Sons, Ltd.
  • Ghahramani, A., de Courten, M., & Prokofieva, M. (2022). The potential of social media in health promotion beyond creating awareness: an integrative review. BMC public health, 22(1), 2402. https://doi.org/10.186/s12889-022-14885-0.
  • Gronholm, P. C., & Thornicroft, G. (2022). Impact of celebrity disclosure on mental health-related stigma. Epidemiology and psychiatric sciences, 31, e62. https://doi.org/10.1017/S2045796022000488.
  • Hadikhah Mozhdehi, M., & Eftekhari Moghadam, A. (2023). Textual emotion detection utilizing a transfer learning approach. The Journal of Supercomputing, 79(12), 13075-13089. https://doi.org/10.1007/s11227-023-05168-5.
  • Hajizadeh, A., Amini, H., Heydari, M., & Rajabi, F. (2024). How to combat stigma surrounding mental health disorders: a scoping review of the experiences of different stakeholders. BMC psychiatry, 24(1), 782. https://doi.org/10.1186/s12888-024-06220-1.
  • Herrera-Peco, I., Fernández-Quijano, I., & Ruiz-Núñez, C. (2023). The role of social media as a resource for mental health care. European journal of investigation in health, psychology and education, 13(6), 1026-1028. https://doi.org/10.3390/ejihpe13060078.
  • Hyman, S. E. (2023). The biology of mental disorders: Progress at last. Dædalus, 152(4), 186-211. https://doi.org/10.1162/daed_a_02038.
  • İş, H., & Tuncer, T. (2021). A Profile Analysis of User Interaction in Social Media Using Deep Learning. Traitement du signal, 38(1). https://doi.org/10.18280/ts.380101.
  • İş, H., & Tuncer, T. (2019). Interaction-based behavioral analysis of twitter social network accounts. Applied Sciences, 9(20), 4448. https://doi.org/10.3390/app9204448.
  • Kina, E. (2025). TLEABLCNN: Brain and Alzheimer’s disease detection using attention-based explainable deep learning and SMOTE using imbalanced brain MRI. IEEE Access, 13, 27670–27683. https://doi.org/10.1109/ACCESS.2025.3539550.
  • Kına, E., & Biçek, E. (2024). Machine Learning Approach for Emotion Identification and Classification in Bitcoin Sentiment Analysis. Yüzüncü Yıl Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 29(3), 913-926. https://doi.org/10.53433/yyufbed.1532649.
  • Kına, E., & Biçek, E. (2023). Tweetlerin duygu analizi için hibrit bir yaklaşım. Doğu Fen Bilimleri Dergisi, 6(1), 57-68. https://doi.org/10.57244/dfbd.1314901.
  • Koca, M., & Avcı, İ. (2024a). Enhancing Network Security: A Comprehensive Analysis of Intrusion Detection Systems. Yüzüncü Yıl Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 29(3), 927–938. https://doi.org/10.53433/yyufbed.1545033.
  • Koca, M., & Avcı, İ. (2024b). Optimization Planning Techniques with Meta-Heuristic Algorithms in IoT: Performance and QoS Evaluation. Sakarya University Journal of Computer and Information Sciences, 7(2), 173-18. https://doi.org/10.35377/saucis...1452049.
  • Mental health of adolescents. (2021). https://www.who.int/news-room/fact-sheets/detail/adolescent-mental-health (accessed 01.01.2025)
  • Mujahid, M., Lee, E., Rustam, F., Washington, P. B., Ullah, S., Reshi, A. A., & Ashraf, I. (2021). Sentiment analysis and topic modeling on tweets about online education during COVID-19. Applied Sciences, 11(18), 8438. https://doi.org/10.3390/app11188438.
  • Nguyen, V. C., Birnbaum, M., & De Choudhury, M. (2023). Understanding and Mitigating Mental Health Misinformation on Video Sharing Platforms. arXiv preprint arXiv:2304.07417. https://doi.org/10.48550/arXiv.2304.07417.
  • Pacheco, J. P., Giacomin, H. T., Tam, W. W., Ribeiro, T. B., Arab, C., Bezerra, I. M., & Pinasco, G. C. (2017). Mental health problems among medical students in Brazil: a systematic review and meta-analysis. Brazilian Journal of Psychiatry, 39, 369–378. https://doi.org/10.1590/1516-4446-2017-2223.
  • P Plutchik, R. (2003). Emotions and life: Perspectives from psychology, biology, and evolution. American Psychological Association.
  • Prizeman, K., Weinstein, N., & McCabe, C. (2023). Effects of mental health stigma on loneliness, social isolation, and relationships in young people with depression symptoms. BMC psychiatry, 23(1), 527. https://doi.org/10.1186/s12888-023-04991-7.
  • Skaik, R., & Inkpen, D. (2020). Using social media for mental health surveillance: a review. ACM Computing Surveys (CSUR), 53(6), 1-31. https://doi.org/10.1145/3422824.
  • Suman, S. K., Shalu, H., Agrawal, L. A., Agrawal, A., & Kadiwala, J. (2020). A novel sentiment analysis engine for preliminary depression status estimation on social media. arXiv preprint arXiv:2011.14280. https://doi.org/10.48550/arXiv.2011.14280.
  • Zollo, F., Baronchelli, A., Betsch, C., Delmastro, M., & Quattrociocchi, W. (2024). Understanding the complex links between social media and health behaviour. BMJ, 385:e075645. https://doi.org/10.1136/bmj-2023-075645.
Toplam 29 adet kaynakça vardır.

Ayrıntılar

Birincil Dil Türkçe
Konular Doğal Dil İşleme
Bölüm Bilgisayar Mühendisliği
Yazarlar

Erol Kına 0000-0002-7785-646X

Yayımlanma Tarihi 3 Eylül 2025
Gönderilme Tarihi 7 Mayıs 2025
Kabul Tarihi 11 Haziran 2025
Yayımlandığı Sayı Yıl 2025 Cilt: 28 Sayı: 3

Kaynak Göster

APA Kına, E. (2025). TRANSFORMER TABANLI DUYGU SINIFLANDIRMASI İLE SOSYAL MEDYADA RUH SAĞLIĞINA İLİŞKİN TÜRKÇE YORUMLARIN ANALİZİ. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 28(3), 1499-1511. https://doi.org/10.17780/ksujes.1694291
 Kapak Resmi İndir