Volume: 2 Issue: 2
Year: 2025, Page: 74-80, Doi: https://doi.org/10.70968/ijeaca.v2i2.ML117
Received: July 29, 2025 Accepted: Nov. 28, 2025 Published: Dec. 12, 2025
Due to the rising popularity of social media, the necessity of automated systems that can monitor, detect harmful content, find sentiment, and detect emerging trends is becoming more urgent [1,2]. A unified Natural Language processing(NLP)[6] pipeline performing sentiment analysis and trend extraction using deep learning methods is proposed in this work. Through public APIs, live textual data is gathered and passed through preprocessing steps after which TF-IDF based feature extraction and initial polarity checking [6,7]. For a better understanding of sentiment patterns, an adapted RoBERTa model is used, and its performance is evaluated compared to widely used Machine Learning methods. According to the experimental observations, RoBERTa shows more robustness and deals with informal social media language better than others. The framework not only entails the sentiment classification of user tweets but also detecting trending topics by the trend in the frequency of keywords and temporal topic model[5,10]. This combination allows to keep a record of the discussions and its time patterns. In general, the suggested method provides a scalable and efficient solution for social media analytics as well as automated content monitoring[12,16].
Keywords: Enhancing Social Media Analytics with NLP Pipeline for Trend Detection and Sentiment
1. Kausar S, Tahir B, Mehmood MA. Manipify: An Automated Framework for Detecting Manipulators in Twitter Trends. Journal of Social Computing. 2023; 4 (1). Available from: https://doi.org/10.23919/jsc.2023.0001
2. Khan ZA, Xia Y, Ali S, Khan JA, Askar SS, Abouhawwash M, <I>et al</I>. Identifying Hot Topic Trends in Streaming Text Data Using News Sequential Evolution Model Based on Distributed Representations. IEEE Access. 2023; 11 Available from: https://doi.org/10.1109/access.2023.3312764
3. Wang A, Jiang H, Ma Y, Jiang J, Liu A, Okazaki N. Improving Implicit Sentiments Analysis via Explanations of Multiple Perspectives. IEEE Access. 2025; 13 Available from: https://doi.org/10.1109/access.2025.3556762
4. Fontes T, Murços F, Carneiro E, Ribeiro J, Rossetti RJF. Leveraging Artificial Intelligence to Write Strategic Content on Social Media Platforms: A Tool-Based Approach. IEEE Open Journal of Intelligent Transportation Systems. 2023; 4 Available from: https://doi.org/10.1109/OJITS.2023.3308210
5. Lobanova PA, Kuzminov IF, Karatetskaia EY, Sabidaeva EA, Anpilogov VV. Trend Detection Using NLP as a Mechanism of Decision Support. Scientific and Technical Information Processing. 2023; 50 (5). Available from: https://doi.org/10.3103/s0147688223050106
6. Sun W, Xiao R, Li X. Online Public Opinion Situation Assessment by Deep Sparse Autoencoder and Time-Series Modeling Convolutional Neural Network. IEEE Access. 2025; 13 Available from: https://doi.org/10.1109/access.2025.3602491
7. Gupta T, Rai A, Roy S. SentimentMapper: A framework for mapping of sentiments towards disaster response using social media data. Applied Intelligence. 2025; 55 (7). Available from: https://doi.org/10.1007/s10489-025-06442-0
8. Yang Y, Fan C, Gong Y, Yeoh W, Li Y. Forwarding in Social Media: Forecasting Popularity of Public Opinion With Deep Learning. IEEE Transactions on Computational Social Systems. 2025; 12 (2). Available from: https://doi.org/10.1109/tcss.2024.3468721
9. Alfreihat M, Almousa OS, Tashtoush Y, AlSobeh A, Mansour K, Migdady H. Emo-SL Framework: Emoji Sentiment Lexicon Using Text-Based Features and Machine Learning for Sentiment Analysis. IEEE Access. 2024; 12 Available from: https://doi.org/10.1109/access.2024.3382836
10. Narejo KR, Zan H, Oralbekova D, Dharmani KP, Orken M, Mukhsina K. Enhancing Emoji-Based Sentiment Classification in Urdu Tweets: Fusion Strategies With Multilingual BERT and Emoji Embeddings. IEEE Access. 2024; 12 Available from: https://doi.org/10.1109/access.2024.3446897
11. Sherin A, Jeya IJS, Deepa SN. Enhanced Aquila Optimizer Combined Ensemble Bi-LSTM-GRU With Fuzzy Emotion Extractor for Tweet Sentiment Analysis and Classification. IEEE Access. 2024; 12 Available from: https://doi.org/10.1109/access.2024.3464091
12. Razali MN, Manaf SA, Hanapi RB, Salji MR, Chiat LW, Nisar K. Enhancing Minority Sentiment Classification in Gastronomy Tourism: A Hybrid Sentiment Analysis Framework With Data Augmentation, Feature Engineering and Business Intelligence. IEEE Access. 2024; 12 Available from: https://doi.org/10.1109/access.2024.3362730
13. Li X, Yang H, Sun X, Wei F. A Multimodal Aspect-Level Sentiment Analysis Model Based on Syntactic-Semantic Perception. IEEE Access. 2025; 13 Available from: https://doi.org/10.1109/access.2025.3624546
14. Shafikuzzaman M, Islam MR, Rolli AC, Akhter S, Seliya N. An Empirical Evaluation of the Zero-Shot, Few-Shot, and Traditional Fine-Tuning Based Pretrained Language Models for Sentiment Analysis in Software Engineering. IEEE Access. 2024; 12 Available from: https://doi.org/10.1109/access.2024.3439450
15. Mughal N, Mujtaba G, Shaikh S, Kumar A, Daudpota SM. Comparative Analysis of Deep Natural Networks and Large Language Models for Aspect-Based Sentiment Analysis. IEEE Access. 2024; 12 Available from: https://doi.org/10.1109/access.2024.3386969
16. Tan X, Zhuang M, Lu X, Mao T. An Analysis of the Emotional Evolution of Large-Scale Internet Public Opinion Events Based on the BERT-LDA Hybrid Model. IEEE Access. 2021; 9 Available from: https://doi.org/10.1109/access.2021.3052566
17. Roy SS, Roy A, Samui P, Gandomi M, Gandomi AH. Hateful Sentiment Detection in Real-Time Tweets: An LSTM-Based Comparative Approach. IEEE Transactions on Computational Social Systems. 2024; 11 (4). Available from: https://doi.org/10.1109/tcss.2023.3260217
18. Maroof A, Wasi S, Jami SI, Siddiqui MS. Aspect-Based Sentiment Analysis for Service Industry. IEEE Access. 2024; 12 Available from: https://doi.org/10.1109/access.2024.3440357
19. Mahmoudi A, Jemielniak D, Ciechanowski D. Assessing Accuracy: A Study of Lexicon and Rule-Based Packages in R and Python for Sentiment Analysis. IEEE Access. 2024; 12 Available from: https://doi.org/10.1109/access.2024.3353692
20. Durga P, Godavarthi D. Deep-Sentiment: An Effective Deep Sentiment Analysis Using a Decision-Based Recurrent Neural Network (D-RNN). IEEE Access. 2023; 11 Available from: https://doi.org/10.1109/access.2023.3320738
© 2025 Ladhane, et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Ladhane P, Talole S, Gadsing S, Pund N, Shahaji B. Enhancing Social Media Analytics with NLP Pipeline for Trend Detection and Sentiment. 2025;2(2):74-80. https://doi.org/10.70968/ijeaca.v2i2.ML117