LinBGN-Net: A Unified Linguistic Framework for Multi-Task Text Classification in Telugu Using BERT, GCN, and Naive Bayes

Authors

  • Asif Hussain Shaik

    Centre for Research and Consultancy, Middle East college, Muscat 113, Oman
  • Fahimuddin Shaik

    Department of ECE, Annamacharya University, Rajampet 516126, India
  • Karimullah Shaik

    Department of ECE, Annamacharya University, Rajampet 516126, India
  • Sureshbabu G

    Department of ECE, Annamacharya University, Rajampet 516126, India Department of MECH, Annamacharya University, Rajampet516126, India

DOI:

https://doi.org/10.30564/fls.v7i7.9470
Received: 12 April 2025 | Revised: 14 May 2025 | Accepted: 16 May 2025 | Published Online: 15 July 2025

Abstract

Despite the growing interest in Natural Language Processing (NLP), linguistically grounded multi-task modeling for low-resource languages like Telugu remains underexplored, particularly across semantically complex tasks such as sentiment, emotion, hate speech, sarcasm, and clickbait detection. This study aims to address this gap by conducting a comprehensive linguistic analysis of Telugu texts through the lens of computational modeling. To that end, we propose LinBGN-Net, an innovative ensemble deep learning framework that integrates BERT for contextual embedding, Graph Convolutional Networks (GCN) for structural understanding, and Naive Bayes (NB) for statistical grounding. The model is trained on five well-balanced Telugu datasets (totalling over 250,000 sentences) from Hugging Face, covering diverse label spaces (2 to 5 classes), thus facilitating an in-depth linguistic study across varied text genres and expressions. LinBGN-Net achieves macro-F1 scores of 0.86 (Sentiment), 0.84 (Emotion), 0.93 (Hate Speech), 0.92 (Sarcasm), and 0.95 (Clickbait), outperforming standard baselines such as Naive Bayes, SVM, LSTM, and even standalone BERT by margins of 2–8% across tasks. The results not only demonstrate the effectiveness of LinBGN-Net as a high-performing multi-task model, but also offer valuable linguistic insights into how Telugu expressions of sentiment, emotion, intent, and persuasion can be computationally modeled and understood—contributing significantly to both linguistic research and real-world NLP applications.

Keywords:

Linguistic Analysis; Telugu; Language; NLP; Emotion; Sarcasm; Sentiment

References

[1] Jaiswal, S., Yadav, R., Roselind, J.D., 2023. Emotion Detection using Natural Language Process. International Journal of Scientific Methods in Intellegence Engineering Networks. 01(03), 01–12.

[2] Álvarez Núñez, A., Santiago Díaz, M. del C., et al., 2024. Emotion detection using natural language processing. International Journal of Combinatorial Optimization Problems and Informatics. 15(5), 108–114. DOI: https://doi.org/10.61467/2007.1558.2024.v15i5.564

[3] Seal, D., Roy, U.K., Basak, R., 2020. Sentence-Level Emotion Detection from Text Based on Semantic Rules. In: Tuba, M., Akashe, S., Joshi, A. (eds.). Information and Communication Technology for Sustainable Development. Advances in Intelligent Systems and Computing, vol 933. Springer: Singapore. DOI: https://doi.org/10.1007/978-981-13-7166-0_42

[4] Kane, A., Patankar, S., Khose, S., et al., 2022. Transformer based ensemble for emotion detection (Version 2). arXiv. 15–24. DOI: https://doi.org/10.48550/arXiv.2203.11899

[5] Kane, A., Patankar, S., Khose, S., et al., 2022. Transformer based ensemble for emotion detection. In Barnes, J., Clercq, O.D., Barriere, V., et al. (Eds.). In Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis. Association for Computational Linguistics. pp. 250–254. DOI: https://doi.org/10.18653/v1/2022.wassa-1.25

[6] Cahyani D.E., Wibawa A.P., Prasetya D.D. et al., 2022. Emotion Detection in Text Using Convolutional Neural Network. In Proceedings of the 2022 International Conference on Electrical and Information Technology (IEIT), Malang, Indonesia, 15–16 September 2022; pp. 372–376. DOI: https://doi.org/10.1109/IEIT56384.2022.9967913

[7] Aditya K., Shantanu P., Sahil K., et al., 2022. García Transformer Based Ensemble for Emotion Detection. ArXiv.org. DOI: https://doi.org/10.48550/arxiv.2203.11899

[8] Perikos, I., Hatzilygeroudis, I., 2013. Recognizing Emotion Presence in Natural Language Sentences. In: Iliadis, L., Papadopoulos, H., Jayne, C. (eds.). Engineering Applications of Neural Networks. EANN 2013. Communications in Computer and Information Science, vol 384. Springer: Berlin/Heidelberg, Germany. DOI: https://doi.org/10.1007/978-3-642-41016-1_4

[9] López‐López, A., García-Gorrostieta, J. M., 2024. Emotion detection in educational dialogues by transfer learning. Journal of Intelligent and Fuzzy Systems. 1–11. DOI: https://doi.org/10.3233/jifs-219340

[10] Chul M.L., Narayanan. S., March, 2005. Toward detecting emotions in spoken dialogs. IEEE Transactions on Speech and Audio Processing. 13(2), 293–303. DOI: https://doi.org/10.1109/TSA.2004.838534

[11] Jeđud, I., 2018. Interdisciplinary approach to emotion detection from text. XA Proceedings. Zagreb: English Student Club. 1(1), 34–72.

[12] Prajapati, Y., Khande, R., Parasar, A., 2023. Sentiment Analysis of Emotion Detection Using Natural Language Processing. In: Kumar, S., Hiranwal, S., Purohit, S.D., et al. (eds.). In Proceedings of the International Conference on Communication and Computational Technologies. Algorithms for Intelligent Systems. Springer: Singapore. DOI: https://doi.org/10.1007/978-981-19-3951-8_18

[13] Wang, Y., Wang, Z., Han, N., et al., 2024. Knowledge distillation from monolingual to multilingual models for intelligent and interpretable multilingual emotion detection. In Clercq, O.D , Barriere, V., Barnes, J., et al. (Eds.). In Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis, Bangkok, Thailand; pp. 470–475. DOI: https://doi.org/10.18653/v1/2024.wassa-1.45

[14] Viraraghavan, V.S., Gavas, R.D., Ramakrishnan, R.K., 2020. Role of emotion words in detecting emotional valence from speech. Proc. Workshop on Speech, Music and Mind (SMM 2020), 26–30. DOI: https://doi.org/10.21437/SMM.2020-6

[15] Nadia A., Abdallah T., Feras A.O., et al., 2023. Towards Enhanced Identification of Emotion from Resource-Constrained Language through a novel Multilingual BERT Approach. ACM Transactions on Asian and Low-Resource Language Information Processing. DOI: https://doi.org/10.1145/3592794

[16] Senem K.M., Hatice E.G., 2024. Hybrid Emotion Detection with Word Embeddings in a Low Resourced Language: Turkish. International Journal of Advanced Computer Science and Applications (ijacsa). 15(6). DOI: http://dx.doi.org/10.14569/IJACSA.2024.01506145

[17] Sahoo, A.K., Kavya, R.V., 2024. Text-Based Emotion Detection: A Deep Learning Approach Using Big Data and Semantic Text Analysis for Human Emotion Detection . IN proceedings of the 3rd International Conference on Optimization Techniques in the Field of Engineering (ICOFE-2024), November 15, 2024. DOI: http://dx.doi.org/10.2139/ssrn.5079858

[18] Aribowo, A.S., Khomsah, S., 2021. Implementation Of Text Mining for Emotion Detection Using the Lexicon Method (Case Study: Tweets About Covid-19). Telematika : Jurnal Informatika dan Teknologi Informasi.18(1), 49–60. DOI: https://doi.org/10.31315/TELEMATIKA.V18I1.4341

[19] Yue, T., Chen, C., Zhang, S., et al., 2018. Ensemble of Neural Networks with Sentiment Words Translation for Code-Switching Emotion Detection. In: Zhang, M., Ng, V., Zhao, D., Li, S., Zan, H. (eds.). In Proceedings of the Natural Language Processing and Chinese Computing. 14 August 2018. DOI: https://doi.org/10.1007/978-3-319-99501-4_37

[20] Darekar, R.V., Dhand, A.P., 2016. Improving emotion detection with speech by enhanced approach. In Proceedings of the 2016 3rd International Conference on Signal Processing and Integrated Networks (SPIN), Noida, India, 11-12 February 2016; pp. 364–369. DOI: https://doi.org/10.1109/SPIN.2016.7566720

[21] Mounika, M., 2022. Model Repository. Available from: https://huggingface.co/mounikaiiith (cited 11 April 2025).

[22] Marreddy, M., Oota, S., Vakada, S, et al., 2021. Clickbait Detection in Telugu: Overcoming NLP Challenges in Resource-Poor Languages using Benchmarked Techniques. 1-8. DOI: https://doi.org/10.1109/IJCNN52387.2021.9534382

[23] Marreddy, M., Oota, S.R., Vakada, L.S., et al., 2022. Multi-task text classification using graph convolutional networks for large-scale low resource language. ArXiv.org. DOI: https://doi.org/10.48550/arXiv.2205.01204

[24] Marreddy, M., et al. Am I a Resource-Poor Language? Data Sets, Embeddings, Models and Analysis for Four Different NLP Tasks in Telugu Language. ACM Transactions on Asian and Low-Resource Language Information Processing. 22(1), 2023. DOI: https://doi.org/10.1145/3531535

[25] Karim, M.A., Abdullah, M.Z., Deifalla, A.F., 2023. An assessment of the processing parameters and application of fibre-reinforced polymers (FRPs) in the petroleum and natural gas industries: A review. Results in Engineering. 18, 101091. DOI: https://doi.org/10.1016/j.rineng.2023.101091

[26] Karim, M.A., Abdullah, M.Z., Waqar, A., et al., 2023. Analysis of the mechanical properties of the single layered braid reinforced thermoplastic pipe (BRTP) for oil & gas industries. Results in Engineering. 20, 101483. DOI: https://doi.org/10.1016/j.rineng.2023.101483

[27] Waqar, A., Othman, I., Aiman, M.S., et al, 2023. Analyzing the success of adopting Metaverse in construction industry: Structural equation modelling. Journal of Engineering. DOI: https://doi.org/10.1155/2023/8824795

[28] Karim, M.A., Abdullah, M.Z., Ahmed, T., 2021. An overview: The processing methods of fiber-reinforced polymers (FRPs). International Journal of Mechanical Engineering and Technology (IJMET). 12(2), 10–24. DOI: https://doi.org/10.34218/IJMET.12.2.2021.002.

[29] Harahap, P., Rimbawati, R., Evalina, N., et al., 2024. Power Conversion from Solar Panels using a 3000-watt Inverter. Journal of Advanced Research in Fluid Mechanics and Thermal Sciences. 124(2), 260–272. DOI: https://doi.org/10.37934/arfmts.124.2.260272

[30] Cholish, C., Rusdi, M., Rahmawaty, R., 2024. Performance Measurement of Peltier Element Design using Solar Test Simulator Concerning Light and Temperature Parameters. Journal of Advanced Research in Fluid Mechanics and Thermal Sciences. 123(2), 231–243. DOI: https://doi.org/10.37934/arfmts.123.2.231243

[31] Abdullah, A., Putri, M., Syahruddin, M., et al., 2024. Optimization of Solar Power Plant with Variation of Solar Reflector Angles and Use of Passive Cooling Integrated Internet of Things. Journal of Advanced Research in Fluid Mechanics and Thermal Sciences. 124(1), 233–248. DOI: https://doi.org/10.37934/arfmts.124.1.233248

Downloads

How to Cite

Shaik, A. H., Shaik, F., Shaik, K., & G, S. (2025). LinBGN-Net: A Unified Linguistic Framework for Multi-Task Text Classification in Telugu Using BERT, GCN, and Naive Bayes. Forum for Linguistic Studies, 7(7), 518–539. https://doi.org/10.30564/fls.v7i7.9470

Issue

Vol. 7 , Iss. 7 (July 2025): In progress

Article Type

Article

License

Copyright © 2025 Asif Hussain Shaik, Fahimuddin Shaik, Karimullah Shaik, Sureshbabu G

Creative Commons License

This is an open access article under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License.