Abstract

Natural Language Processing (NLP) has emerged as an enabler for automation and intelligence for the telecom industry, driving applications such as customer sentiment analysis, network management, and technical document processing. This systematic review examines 20 peer-reviewed studies between 2020 and 2025 across three key use cases: customer experience improvement (35%), technical document mining (30%), and network management automation (25%). Domain-specific language models like Tele-LLMs and retrieval-augmented generation (RAG) models consistently beat general-purpose models like GPT-4, reaching up to 23% higher telecom-specific benchmark accuracy. Edge deployment breakthroughs like pruning, quantization, and distillation facilitate up to 4× reduced latency for real-time inference, maintaining up to 95% of the original performance of the model. Challenges that still exist include scarcities of data, multilingual support, integration with legacy systems, and concepts that drift through the fast pace of standards development. This review outlines current capabilities, describes the gap between current research and published papers in Dongyu et al., and outlines some potential future directions such as federated learning, multimodal model design, and hybrid edge-cloud deployment to enable NLP applications to advance to next-generation telecommunications networks.

References

• A. Maatouk, K. C. Ampudia, R. Ying, and L. Tassiulas, "Tele-LLMs: A Series of Specialized Large Language Models for Telecommunications," arXiv preprint, Sep. 024. [Online]. Available: https://arxiv.org/abs/2409.05314 [Accessed: 03 Jun. 2025].
• A.-L. Bornea, F. Ayed, A. De Domenico, N. Piovesan, and A. Maatouk, "Telco-RAG: Navigating the Challenges of Retrieval-Augmented Language Models for Telecommunications," arXiv preprint, Apr. 2024. [Online]. Available: https://arxiv.org/abs/2404.15939 [Accessed: 03 Jun. 2025].
• F. A. Rodriguez Yaguache, "Technical Language Processing for Telecommunications Specifications," arXiv preprint, Jun. 2024. [Online]. Available: https://arxiv.org/abs/2406.02325 [Accessed: 03 Jun. 2025].
• A. Karapantelakis, M. Thakur, A. Nikou, A. Mostafa, M. Jaber, and N. Nikaein, "Using Large Language Models to Understand Telecom Standards," in Proc. IEEE Int. Conf. Machine Learn. Commun. Netw. (ICMLCN), Apr. 2024. [Online]. Available: https://arxiv.org/abs/2404.02929 [Accessed: 03 Jun. 2025].
• J. R. Jim, M. A. R. Talukder, P. Malakar, F. Akter, and M. F. A. Gaffar, "Recent advancements and challenges of NLP-based sentiment analysis: A state-of-the-art review," Nat. Lang. Process. J., vol. 6, Art. no. 100059, Mar. 2024. [Online]. Available: https://doi.org/10.1016/j.nlp.2024.100059 [Accessed: 03 Jun. 2025].
• N. Ahmed, A. K. Saha, M. A. Al Noman, A. M. M. Uddin, M. M. Rahman, and M. S. Islam, "Deep learning-based natural language processing in human–agent interaction: Applications, advancements and challenges," Nat. Lang. Process. J., vol. 7, Art. no. 100112, Jun. 2024. [Online]. Available: https://doi.org/10.1016/j.nlp.2024.100112 [Accessed: 03 Jun. 2025].
• T. Ahmed, N. Piovesan, A. De Domenico, and M. Debbah, "Linguistic Intelligence in Large Language Models for Telecommunications," arXiv preprint, Feb. 2024. [Online]. Available: https://arxiv.org/abs/2402.15818 [Accessed: 03 Jun. 2025].
• A. De Domenico, N. Piovesan, and F. Ayed, "Chat3GPP: An Open-Source Retrieval-Augmented Generation Framework for 3GPP Documents," ResearchGate, 2024. [Online]. Available: https://www.researchgate.net/publication/388402418 [Accessed: 03 Jun. 2025].
• A. Maatouk, F. Ayed, N. Piovesan, A. De Domenico, and M. Debbah, "Large Language Models for Telecom: Forthcoming Impact on the Industry," IEEE Commun. Mag., vol. 62, no. 4, pp. 134–140, Aug. 2023. [Online]. Available: https://arxiv.org/abs/2308.06013 [Accessed: 03 Jun. 2025].
• A. Maatouk, F. Ayed, N. Piovesan, A. De Domenico, and M. Debbah, "TeleQnA: A Benchmark Dataset to Assess Large Language Models Telecommunications Knowledge," arXiv preprint, Oct. 2023. [Online]. Available: https://arxiv.org/abs/2310.15051 [Accessed: 03 Jun. 2025].
• S. Tuli and N. K. Jha, "EdgeTran: Co-designing Transformers for Efficient Inference on Mobile Edge Platforms," IEEE Trans. Mobile Comput., vol. 23, no. 5, pp. 5820–5834, May 2024. [Online]. Available: https://arxiv.org/abs/2303.13745 [Accessed: 03 Jun. 2025].
• D. G. Riviello, R. Tuninato, E. Zimaglia, R. Fantini, and R. Garello, "Implementation of Deep-Learning-Based CSI Feedback Reporting on 5G NR-Compliant Link-Level Simulator," Sensors, vol. 23, no. 2, Art. no. 910, Jan. 2023. [Online]. Available: https://www.mdpi.com/1424-8220/23/2/910 [Accessed: 03 Jun. 2025].
• S. Nithuna and C. A. Laseena, "Review on Implementation Techniques of Chatbot," in Proc. Int. Conf. Commun. Signal Process. (ICCSP), Jul. 2020, pp. 496–501. [Online]. Available: https://ieeexplore.ieee.org/document/9182168 [Accessed: 03 Jun. 2025].
• K. L. Tan, C. P. Lee, K. S. M. Anbananthen, and K. M. Lim, "RoBERTa-LSTM: A Hybrid Model for Sentiment Analysis With Transformer and Recurrent Neural Network," IEEE Access, vol. 10, pp. 21517–21525, 2022. [Online]. Available: https://ieeexplore.ieee.org/document/9714048. doi: 10.1109/ACCESS.2022.3152828 [Accessed: 03 Jun. 2025].
• B. C. Allen, K. J. Stubbs, and W. E. Dixon, "Data-Based and Opportunistic Integral Concurrent Learning for Adaptive Trajectory Tracking During Switched FES-Induced Biceps Curls," IEEE Trans. Neural Syst. Rehabil. Eng., vol. 30, pp. 2557–2566, 2022. [Online]. Available: https://ieeexplore.ieee.org/document/9875948 [Accessed: 03 Jun. 2025].
• D. Anny, "Integrating Natural Language Processing (NLP) in Telecom Customer Support: Enhancing Issue Diagnosis and Resolution," ResearchGate, 2025. [Online]. Available: ttps://www.researchgate.net/publication/390726141 [Accessed: 03 Jun. 2025].
• L. Almuqren and A. Cristea, "AraCust: a Saudi Telecom Tweets corpus for sentiment analysis," PeerJ Comput. Sci., vol. 7, Art. no. e510, May 2021. [Online]. Available: https://peerj.com/articles/cs-510/ [Accessed: 03 Jun. 2025].
• M. R. A. Rahim, S. Abdul-Rahman, and Y. Mahmud, "Customers' Opinions on Mobile Telecommunication Services in Malaysia using Sentiment Analysis," Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 12, pp. 229–238, 2021. [Online]. Available: https://thesai.org/Publications/ViewPaper?Volume=12&Issue=12&Code=ijacsa&SerialNo=29 [Accessed: 03 Jun. 2025].
• S. K. Goudos, P. Trakadas, C. Athanasiadou, C. Zarafetas, A. Arapoglou, and A. Alsharoa, "Machine Learning in Beyond 5G/6G Networks—State-of-the-Art and Future Trends," Electronics, vol. 10, no. 22, Art. no. 2786, Nov. 2021. [Online]. Available: https://www.mdpi.com/2079-9292/10/22/2786 [Accessed: 03 Jun. 2025].
• B. Saputro, M. D. Pratama, A. Putra, and Y. Fitrianto, "Measuring service quality in the telecommunications industry from customer reviews using sentiment analysis: a case study in PT XL Axiata," in Proc. 2nd Int. Conf. Inf. Technol. Syst. Manage. (CITSM), Nov. 2021, pp. 1–6. [Online]. Available: https://www.researchgate.net/publication/354134304 [Accessed: 03 Jun. 2025]