journal article Open Access Apr 05, 2026

Reliability-Aware Multilingual Sentiment Analytics for Agricultural Market Intelligence

Mathematics Vol. 14 No. 7 pp. 1220 · MDPI AG
View at Publisher Save 10.3390/math14071220
Abstract
Public opinion on online platforms now plays an important role in agricultural markets, which have always been unpredictable. Although sentiment analysis has been widely applied to agricultural texts, most existing studies typically focus only on classification accuracy without connecting results to actual market intelligence systems, especially in multilingual contexts. This paper introduces a reliability-aware transformer-based framework for analyzing sentiment in agricultural market intelligence across multiple languages. The framework leverages weakly supervised multilingual transformers to extract sentiment signals from large-scale unlabeled Thai and English texts about major agricultural commodities found online. To enhance robustness under weak supervision, the framework incorporates reliability-aware mechanisms, including confidence-based pseudo-label filtering, cross-source consistency refinement, and expert-guided calibration to reduce noise and account for bias between different data sources. Sentiment predictions are further aligned with market intelligence objectives through reliability-weighted aggregation, yielding interpretable sentiment indices that enable cross-lingual and cross-source comparability. We tested the framework extensively using a multilingual agricultural corpus derived from social media and news coverage of agriculture. The results show consistent improvements over both classical machine learning approaches and standard multilingual transformer baselines. Additional ablation studies and sensitivity analyses confirmed that reliability-aware mechanisms, particularly confidence thresholding, play a crucial role in getting the right balance between label quality and data coverage. Overall, the results indicate that reliability-aware multilingual sentiment analytics provide robust and actionable insights for agricultural market monitoring and policy analysis.
Topics

No keywords indexed for this article. Browse by subject →

References
90
[1]
Davier "Media Analysis on Volatile Markets’ Dynamics and Adaptive Behavior for the Agri-Food System" Int. J. Food Syst. Dyn. (2010) 10.18461/ijfsd.v1i3.135
[2]
Garrido, A., Brümmer, B., M’Barek, R., Meuwissen, M., and Morales-Opazo, C. (2016). Agricultural Markets Instability: Revisiting the Recent Food Crises. Agricultural Markets Instability: Revisiting the Recent Food Crises, Routledge. 10.4324/9781315676265
[3]
Varangis, P., Larson, D., and Anderson, J.R. (2002). Agricultural Markets and Risks: Management of the Latter, Not the Former, World Bank. 10.1596/1813-9450-2793
[4]
Sidhu "Role of Market Intelligence in Agriculture: A Success Story of Basmati Cultivation in Punjab" Indian J. Econ. Dev. (2014) 10.5958/j.2322-0430.10.1a.017
[5]
Tang "Deep Learning for Sentiment Analysis: Successful Approaches and Future Challenges" WIREs Data Min. Knowl. Discov. (2015) 10.1002/widm.1171
[6]
Lv, X., Lin, W., Meng, J., and Mo, L. (2024). Spillover Effect of Network Public Opinion on Market Prices of Small-Scale Agricultural Products. Mathematics, 12. 10.3390/math12040539
[7]
Rizki "Social Media Sentiment Analysis to Understand Agricultural Market Trends and Consumer Preferences" J. Minfo Polgan (2023) 10.33395/jmp.v12i2.12970
[8]
"Natural Language Processing of Social Network Data for the Evaluation of Agricultural and Rural Policies" J. Rural. Stud. (2024) 10.1016/j.jrurstud.2024.103341
[9]
Li "A Novel Text-Based Framework for Forecasting Agricultural Futures Using Massive Online News Headlines" Int. J. Forecast. (2020) 10.1016/j.ijforecast.2020.02.002
[10]
Kherwa, P., Sachdeva, A., Mahajan, D., Pande, N., and Singh, P. (2014). An Approach towards Comprehensive Sentimental Data Analysis and Opinion Mining. Proceedings of the IEEE International Advance Computing Conference, IEEE. 10.1109/iadcc.2014.6779394
[11]
Vohra "Applications and Challenges for Sentiment Analysis: A Survey" Int. J. Eng. Res. Technol. (2013)
[12]
Gunter "Sentiment Analysis: A Market-Relevant and Reliable Measure of Public Feeling?" Int. J. Mark. Res. (2014) 10.2501/ijmr-2014-014
[13]
Tang "The Implications of Utilizing Market Information and Adopting Agricultural Advice for Farmers in Developing Economies" Agric. Econ. (2015)
[14]
Uysal, A., and Murphey, Y. (2017). Sentiment Classification: Feature Selection Based Approaches Versus Deep Learning. Proceedings of the International Conference on Computer and Information Technology, IEEE. 10.1109/cit.2017.53
[15]
Sentiment Analysis Based on Deep Learning: A Comparative Study

Nhan Cach Dang, María N. Moreno-García, Fernando De La Prieta

Electronics 10.3390/electronics9030483
[16]
Dieng, A.B., Wang, C., Gao, J., and Paisley, J. (2016, January 2–4). TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency. Proceedings of the International Conference on Learning Representations, San Juan, Puerto Rico.
[17]
Sun, H., Xu, C., Wu, Y., Zou, S., and Wan, F. (2020). L-CNN: An Improved Convolutional Neural Network to Capture Long-Distance Dependencies. Recent Trends in Decision Science and Management, Springer. 10.1007/978-981-15-3588-8_14
[18]
Abdullah "Multilingual Sentiment Analysis: A Systematic Literature Review" Pertanika J. Sci. Technol. (2021) 10.47836/pjst.29.1.25
[19]
Kumaresan "Sentiment Analysis in Multiple Languages: A Review of Current Approaches and Challenges" REST J. Data Anal. Artif. Intell. (2023)
[20]
Modak "Market Sentiment Analysis Using Multimodal Transformers: Integrating Earnings Calls, Social Media, and Technical Indicators" Glob. J. Eng. Technol. Adv. (2023) 10.30574/gjeta.2023.15.3.0121
[21]
Vizniuk "A Comprehensive Survey of Retrieval-Augmented Large Language Models for Decision Making in Agriculture: Unsolved Problems and Research Opportunities" J. Artif. Intell. Soft Comput. Res. (2024) 10.2478/jaiscr-2025-0007
[22]
Kumar "Real-Time Multilingual Sentiment Analysis and Event Prediction Using Scalable NLP and Big Data Frameworks" Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies (ICRDICCT‘25 2025) (2025) 10.5220/0013871600004919
[23]
Lo "Multilingual Sentiment Analysis: From Formal to Informal and Scarce Resource Languages" Artif. Intell. Rev. (2016) 10.1007/s10462-016-9508-4
[24]
Garg "Text Pre-Processing of Multilingual Data for Sentiment Analysis Based on Social Network Data" Int. J. Electr. Comput. Eng. (2022)
[25]
Evaluating the Effectiveness of Text Pre-Processing in Sentiment Analysis

Marco A. Palomino, Farida Aider

Applied Sciences 10.3390/app12178765
[26]
Deriu, J., Lucchi, A., Luca, V.D., Severyn, A., Müller, S., Cieliebak, M., Hofmann, T., and Jaggi, M. (2017). Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification. Proceedings of the Web Conference, ACM. 10.1145/3038912.3052611
[27]
Dong, X., and de Melo, G. (2019). A Robust Self-Learning Framework for Cross-Lingual Text Classification. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Association for Computational Linguistics. 10.18653/v1/d19-1658
[28]
He "Self-Training from Labeled Features for Sentiment Analysis" Inf. Process. Manag. (2011) 10.1016/j.ipm.2010.11.003
[29]
Lowphansirikul, L., Polpanumas, C., Jantrakulchai, N., and Nutanong, S. (2021). WangchanBERTa: Pretraining Transformer-Based Thai Language Models. arXiv.
[30]
Thiengburanathum "SETAR: Stacking Ensemble Learning for Thai Sentiment Analysis Using RoBERTa and Hybrid Feature Representation" IEEE Access (2023) 10.1109/access.2023.3308951
[32]
Zhou, J., Tian, J., Wang, R., Wu, Y., Xiao, W., and He, L. (2020). SentiX: A Sentiment-Aware Pre-Trained Model for Cross-Domain Sentiment Analysis. Proceedings of the 28th International Conference on Computational Linguistics, International Committee on Computational Linguistics. 10.18653/v1/2020.coling-main.49
[33]
Cao, Z., Chen, E., Huang, Y., Shen, S., and Huang, Z. (2023). Learning from Crowds with Annotation Reliability. Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, ACM. 10.1145/3539618.3592007
[34]
Zhao, L., Sukthankar, G., and Sukthankar, R. (2011). Robust Active Learning Using Crowdsourced Annotations for Activity Recognition. Human Computation, Proceedings of the AAAI Workshop on Human Computation, AAAI Press.
[35]
Aliyu "Sentiment Analysis in Low-Resource Settings: A Comprehensive Review of Approaches, Languages, and Data Sources" IEEE Access (2024) 10.1109/access.2024.3398635
[36]
Kouadri, W.M., Benbernou, S., Ouziri, M., and Ben Amor, I. (2022). WSSA: Weakly Supervised Semantic-Based Approach for Sentiment Analysis. Proceedings of the International Conference on Statistical and Scientific Database Management, Association for Computing Machinery.
[37]
Rastogi, S. (2023). Weak Supervision and Transformer-Based Sentiment Analysis on Multilingual Data. Proceedings of the International Conference on Communication Systems and Networks, IEEE. 10.1109/comsnets56262.2023.10041286
[38]
Tseng, Y.-M., Chen, W.-L., Chen, C.-C., and Chen, H.-H. (2024). Are Expert-Level Language Models Expert-Level Annotators?. arXiv.
[39]
Mishev "Evaluation of Sentiment Analysis in Finance: From Lexicons to Transformers" IEEE Access (2022) 10.1109/access.2020.3009626
[40]
Mozetič, I., Grčar, M., and Smailović, J. (2016). Multilingual Twitter Sentiment Classification: The Role of Human Annotators. PLoS ONE, 11. 10.1371/journal.pone.0155036
[41]
Spinde, T. (2021). Towards a Reliable Ground-Truth for Biased Language Detection. Proceedings of the ACM/IEEE Joint Conference on Digital Libraries, IEEE. 10.1109/jcdl52503.2021.00053
[42]
Hernández, S., and Sallis, P. (2011). Sentiment-Preserving Reduction for Social Media Analysis. Proceedings of the Iberoamerican Congress on Pattern Recognition, Springer. 10.1007/978-3-642-25085-9_48
[43]
Yahav "Comments Mining with TF-IDF: The Inherent Bias and Its Removal" IEEE Trans. Knowl. Data Eng. (2019) 10.1109/tkde.2018.2840127
[44]
Baldwin, T., and Li, Y. (2015). An In-Depth Analysis of the Effect of Text Normalization in Social Media. Proceedings of the North American Chapter of the Association for Computational Linguistics, Association for Computational Linguistics. 10.3115/v1/n15-1045
[45]
van der Goot, R. (2019). An In-Depth Analysis of the Effect of Lexical Normalization on the Dependency Parsing of Social Media. Proceedings of the Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics. 10.18653/v1/d19-5515
[46]
Volkova, S., Wilson, T., and Yarowsky, D. (2013). Exploring Demographic Language Variations to Improve Multilingual Sentiment Analysis in Social Media. Proceedings of the Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics. 10.18653/v1/d13-1187
[47]
Petrov, A., La Malfa, E., Torr, P.H.S., and Bibi, A. (2023). Language Model Tokenizers Introduce Unfairness between Languages. Proceedings of the Neural Information Processing Systems Conference, Curran Associates Inc.
[48]
Wen, Y., Xian, Y., Wang, Y., and Yu, Z. (2024). UnifiedCut: A Simple and Efficient Neural Model for Thai, Burmese and Khmer Word Segmentation. Appl. Sci., 14. 10.3390/app142311435
[49]
Han, G., Tsao, J., and Huang, X. (2024). Length-Aware Multi-Kernel Transformer for Long Document Classification. Proceedings of the Semantic Evaluation (STARSEM), Association for Computational Linguistics. 10.18653/v1/2024.starsem-1.22
[50]
Mayatskaya, E. (2024, January 13–15). Long Text Classification with Segmentation. Proceedings of the IEEE Ural-Siberian Conference on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT), Yekaterinburg, Russian. 10.1109/usbereit61901.2024.10583985

Showing 50 of 90 references