SavedAdd your journal

Journals / Balıkesir Üniversitesi Fen Bilimleri Enstitüsü Dergisi / 2026 / Cilt: 28 Sayı: 1

User-based topic, word, and sentiment analysis of Turkish tweets on platform X

X platformunda üzerinde Türkçe tweetlerin kullanıcı bazlı konu, kelime ve duygu analizi

Mehmet Yusuf Bircan(Karamanoğlu Mehmetbey Üniversitesi)0009-0007-5728-3020
Ayşe Eldem(KARAMANOĞLU MEHMETBEY ÜNİVERSİTESİ)0000-0002-5561-1568
Pages
375–394
Publication Date
2026-01-14
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

This study presents an original tool for understanding individuals' interests, emotional states, and mindsets in more detail by providing an in-depth user-based perspective.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Social media platforms, especially X (Twitter), provide rich data sources for understanding social and individual trends.
📊
Key Findings & Data:While existing studies generally focus on general data sets, analyses at the individual user level remain limited.
💡
Conclusion & Impact:This study presents an original tool for understanding individuals' interests, emotional states, and mindsets in more detail by providing an in-depth user-based perspective.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Latent Dirichlet Allocation · Metin Analizi · Duygu Analizi

Abstract

Social media platforms, especially X (Twitter), provide rich data sources for understanding social and individual trends. While existing studies generally focus on general data sets, analyses at the individual user level remain limited. This study aims to fill this gap by presenting a web-based system that extracts and analyzes data from specific users from X. The developed system collects tweets from the desired user using the web scraping technique and preprocesses this data with steps specific to the Turkish language. Then, it applies three basic analyses with Latent Dirichlet Allocation (LDA): topic modeling, sentiment analysis, and word cloud generation. The system visualizes the results of topic distributions, sentiment graphs, and word clouds through a user-friendly interface. This study presents an original tool for understanding individuals' interests, emotional states, and mindsets in more detail by providing an in-depth user-based perspective.

Özet

Sosyal medya platformları, özellikle X (Twitter), toplumsal ve bireysel eğilimleri anlamak için zengin veri kaynakları sunmaktadır. Mevcut çalışmalar genellikle genel veri kümelerine odaklanırken, bireysel kullanıcı düzeyindeki analizler sınırlıdır. Bu çalışma, X'teki belirli kullanıcılardan veri toplayan ve analiz eden web tabanlı bir sistem sunarak bu boşluğu doldurmayı amaçlamaktadır. Geliştirilen sistem, web kazıma tekniğini kullanarak istenen kullanıcıdan tweet toplar ve bu verileri Türkçe diline özgü adımlarla ön işleme tabi tutar. Ardından, Latent Dirichlet Allocation (LDA) ile üç temel analiz uygular: konu modelleme, duygu analizi ve kelime bulutu oluşturma. Sistem, konu dağılımlarının, duygu grafiklerinin ve kelime bulutlarının sonuçlarını kullanıcı dostu bir arayüz aracılığıyla görselleştirir. Bu çalışma, derinlemesine kullanıcı tabanlı bir bakış açısı sunarak bireylerin ilgi alanlarını, duygusal durumlarını ve zihniyetlerini daha ayrıntılı olarak anlamak için özgün bir araç sunmaktadır.

🔖

Cite This Article

Bircan, M. Y., Eldem, A. (2026). User-based topic, word, and sentiment analysis of Turkish tweets on platform X. Balıkesir Üniversitesi Fen Bilimleri Enstitüsü Dergisi, Cilt: 28 Sayı: 1, 375–394. https://doi.org/10.25092/baunfbed.1750569

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (22)

  1. Bilgin, M. and İ.F. Şentürk, Sentiment analysis of tweets based on document vectors using supervised learning and semi-supervised learning Balıkesir Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 21, 2, 822-839, (2019).
  2. Vatambeti, R., et al., Twitter sentiment analysis on online food services based on elephant herd optimization with hybrid deep learning technique, Cluster Computing, 1-5, (2023).
  3. Rabadán-Martín, I., et al., Topic-based engagement analysis: Focusing on hotel industry Twitter accounts, Tourism Management, 106, 104981, (2025).
  4. Martín, M.S., F.-W. Chen, and P.A. Urbistondo, Application of the LDA model to identify topics in telemedicine conversations on the X social network, BMC Health Services Research, 25, 1, 369, (2025).
  5. Dewi, D.A. and T.B. Kurniawan, Exploring Financial Trends through Topic Modeling and Time-Series Analysis: A Clustering Approach Using Latent Dirichlet Allocation (LDA) on Twitter Data, Journal of Digital Society, 1, 1, 91-108, (2025).
  6. Atılgan, K.Ö. and H. Yoğurtcu, Sentiment Analysis of Twitter Posts of Cargo Company Customers Çağ Üniversitesi Sosyal Bilimler Dergisi, 18, 1, 31-39, (2021).
  7. Güneş, Y. and M. Arıkan, X (Twitter) Sentiment Analysis Based on Hybrid Approach: An Application for Online Food Ordering, Bilişim Teknolojileri Dergisi, 18, 2, 143-167, (2025).
  8. Kim, J., D. Kim, and E. Park, I know your stance! Analyzing Twitter users’ political stance on diverse perspectives, Journal of Big Data, 12, 1, 14, (2025).
  9. Kwak, H., et al. What is Twitter, a social network or a news media?, Proceedings of the 19th international conference on World wide web, 591-600, (2010).
  10. Uzun, C., Twitter Mentions of February 6th Earthquake: An Emotional Language Analysis, Doğal Afetler ve Çevre Dergisi, 9, 2, 503–517, (2023).
  11. Kartal, Y., TOJDE Dergisi üzerinde LDA ile konu modelleme. 2017, Anadolu University (Turkey).
  12. Taşbaş Ustaoğlu, E., Conceptualization of Human Robot Interaction Through Word Cloud Analysis Econder Uluslararası Akademik Dergi, 3, 2, 221-239, (2019).
  13. Günyaktı, R.İ. and N. Bursa, Investigation of the Perception toward Health Workers and Teachers on Twitter Data via Sentiment Analysis in the Covid19 Pandemic, Selçuk İletişim, 15, 1, 264-285, (2022).
  14. Seren, N. and M.H. Altıntaş, Turizm İşletmelerinde Marka Kişiliğinin Duygu Analizi Yöntemiyle Belirlenmesi, International Journal of Social Inquiry, 16, 1, 229-254, (2023).
  15. İlhan, N. and D. Sağaltıcı, Sentiment Analysis in Twitter Harran Üniversitesi Mühendislik Dergisi, 5, 2, 146-156, (2020).
  16. Akgül, E.S., C. Ertano, and D. Banu, Sentiment analysis with Twitter, Pamukkale University Journal of Engineering Sciences 22, 2, 106-110, (2016).
  17. Aydın, G. and İ. Hallaç, Automatic Topic Detection on Turkish Text Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 33, 2, 599-606, (2021).
  18. Carle, V., Web Scraping Using Machine Learning. 2020, KTH Royal Institute of Technology, Stockholm, Sweden. p. 1-4.
  19. Çetin, V. and O. Yıldız, A comprehensive review on data preprocessing techniques in data analysis, Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 28, 2, 299-312, (2022).
  20. Can, U. and B. Alatas, Review of Sentiment Analysis and Opinion Mining Algorithms International Journal of Pure and Applied Sciences, 3, 1, 75-111, (2017).
  21. Kabir, A.I., et al., The Power of Social Media Analytics: Text Analytics Based on Sentiment Analysis and Word Clouds on R, Informatica Economica, 22, 1, (2018).
  22. Jelodar, H., et al., Latent Dirichlet allocation (LDA) and topic modeling: models, applications, a survey, Multimedia tools and applications, 78, 15169-15211, (2019).