Volume 22, Issue 1 (5-2025)
JSDP 2025, 22(1): 39-52 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
moradbeiki P, basiri A. Recognizing request and non-request messages in social networks with combined approaches. JSDP 2025; 22 (1) :39-52
URL: http://jsdp.rcisp.ac.ir/article-1-1425-en.html
URL: http://jsdp.rcisp.ac.ir/article-1-1425-en.html
Assistant Professor of Electrical and Computer Engineering Department, Isfahan University of Technology, Isfahan, Iran
Abstract: (185 Views)
The aim of the request recognition task in social networks is to understand the intent behind the posts, comments, or messages shared by users. Many businesses are actively present on various social networks, making it crucial to identify user needs for marketers in this space to foster the growth of online businesses and e-commerce. Detecting request messages automatically and filtering them is essential. However, social network messages often contain slang and numerous spelling errors, posing challenges for research in this domain. While extensive research has been conducted in English, studies on this task in Persian are limited. Telegram stands out as the most popular social network in Iran, with a large Persian-speaking user base. This study utilized a standard labeled Persian dataset from Telegram for training and testing purposes, comprising 85741 messages from the platform, evenly split between request and non-request categories. To tackle the significant challenges posed by sarcastic messages and spelling mistakes on social media platforms, we devised a multi-step hybrid strategy.
The initial step involves preprocessing. Social media data typically consists of unstructured and slang-ridden user messages, necessitating preprocessing to enhance Persian text processing and reduce slang usage. The pre-processing phase is crucial when dealing with social media platforms. Because Telegram is unique compared to other platforms the data cleaning process varies. This study's accomplishment includes developing a unique dataset and filtering out noise from Telegram enhancing improvement in the pre-processing phase. Also, this involves normalizing different word forms, such as "beautiful" and "beauty," to maintain the integrity of word meanings.
The subsequent step focuses on feature extraction. Various approaches to feature extraction come with their own set of advantages and drawbacks. Hence, we employed hybrid feature extraction methods to address this complexity. While Tf-Idf methods assess word importance without considering meaning, FastText retains semantic similarity. By combining the bag of words and FastText methods, our research aims to enhance accuracy. The final step involves classification, where deep learning networks are utilized to evaluate these features.
Experimental findings indicate that our final model achieves precision, recall, and f-score rates of nearly 90%, representing a 5% improvement on average compared to previous methodologies.
The initial step involves preprocessing. Social media data typically consists of unstructured and slang-ridden user messages, necessitating preprocessing to enhance Persian text processing and reduce slang usage. The pre-processing phase is crucial when dealing with social media platforms. Because Telegram is unique compared to other platforms the data cleaning process varies. This study's accomplishment includes developing a unique dataset and filtering out noise from Telegram enhancing improvement in the pre-processing phase. Also, this involves normalizing different word forms, such as "beautiful" and "beauty," to maintain the integrity of word meanings.
The subsequent step focuses on feature extraction. Various approaches to feature extraction come with their own set of advantages and drawbacks. Hence, we employed hybrid feature extraction methods to address this complexity. While Tf-Idf methods assess word importance without considering meaning, FastText retains semantic similarity. By combining the bag of words and FastText methods, our research aims to enhance accuracy. The final step involves classification, where deep learning networks are utilized to evaluate these features.
Experimental findings indicate that our final model achieves precision, recall, and f-score rates of nearly 90%, representing a 5% improvement on average compared to previous methodologies.
Type of Study: Research |
Subject:
Paper
Received: 2024/04/18 | Accepted: 2024/12/4 | Published: 2025/06/21 | ePublished: 2025/06/21
Received: 2024/04/18 | Accepted: 2024/12/4 | Published: 2025/06/21 | ePublished: 2025/06/21
References
1. خبرگزاری جمهوری اسلامی (2021) ، آخرین وضعیت شبکه‌های اجتماعی، https://www.irna.ir/news/
1. https://www.irna.ir/news/ (2021)
2. آ. پیک، م. زارع چاهوکی، م. آقاصرام، «تشخیص پیام‌های درخواست در پیام‌رسان تلگرام مبتنی بر اثربخشی کاهش وضعیت ها در مدل مخفی مارکوف»، دومین کنفرانس بین‌المللی پژوهش‌های کاربردی در علوم برق و کامپیوتر، 1397.
2. A. peyk, M. Zare Chahooki, "Detection of request messages in Telegram messenger based on the effectiveness of reducing situations in the hidden Markov model", Second International Conference on Applied Research in Electrical and Computer Science, 2019.
3. ع. محمدی، م. رضاییان، «تعیین قطبیت نظرات کاربران و تشخیص درخواست ها با کمک تکنیک‌های یادگیری عمیق در تلگرام»، چهارمین کنفرانس ملی تحقیقات کاربردی در مهندسی برق، مکانیک، کامپیوتر و فناوری اطلاعات، 1397.
3. A. Mohammadi, M. Rezaee, "Determining the polarity of users' opinions and recognizing requests with the help of deep learning techniques in Telegram", Fourth National Conference on Applied Research in Electrical Engineering, Mechanics, Computer and Information Technology, 2019.
4. م. دیانتی، م. صدرالدینی، ا. راسخ، ح. تقی‌زاده، «روشی مستقل از زبان جهت ریشه‌یابی کلمات با استفاده از معیار شباهت»، یازدهمین کنفرانس سراسری سیستم های هوشمند، 1391.
4. M. Dianati, M. Sadredini, "A language-independent method for rooting words using similarity criteria", 11th Iranian Conference on Intelligent Systems, 2013.
5. S. Moro, P. Cortez, P. Rita, "Business intelligence in banking: A literature analysis from 2002 to 2013 using text mining and latent Dirichlet allocation", Expert Systems with Applications, vol. 42, no. 3, pp. 1314-24, 2015. [DOI:10.1016/j.eswa.2014.09.024]
6. M. Yang, B. Jiang, Y. Wang, T. Hao, Y. Liu, "News text mining-based business sentiment analysis and its significance in economy", Frontiers in Psychology, vol. 13, pp. 1-7 , 2022. [DOI:10.3389/fpsyg.2022.918447] [PMID] []
7. H. Hassani, C. Beneki, S. Unger, MT. Mazinani, "Text mining in big data analytics", Big Data and Cognitive Computing, vol. 4, no. 1, 2020. [DOI:10.3390/bdcc4010001]
8. A. Gasparetto, M. Marcuzzo, A. Zangari, A. Albarelli, "A survey on text classification algorithms: From text to predictions", Information, vol. 13, no. 2, pp. 83, 2023. [DOI:10.3390/info13020083]
9. F. Greco, A. Polli, "Emotional Text Mining: Customer profiling in brand management", International Journal of Information Management , vol. 51, pp. 101934, 2020. [DOI:10.1016/j.ijinfomgt.2019.04.007]
10. A. Akundi, B. Tseng, J. Wu, E. Smith, "Text mining to understand the influence of social media applications on smartphone supply chain", Procedia Computer Science, vol. 140, pp. 87-94, 2018. [DOI:10.1016/j.procs.2018.10.296]
11. W. He, S. Zha, L. Li, "Social media competitive analysis and text mining: A case study in the pizza industry", International journal of information management, vol. 33, no. 3, pp. 464-72, 2013. [DOI:10.1016/j.ijinfomgt.2013.01.001]
12. W. Souma, I. Vodenska, H. Aoyama, "Enhanced news sentiment analysis using deep learning methods", Journal of Computational Social Science, vol. 2, no. 1, pp. 33-46, 2019. [DOI:10.1007/s42001-019-00035-x]
13. S. Mohan, S. Mullapudi, S. Sammeta, "Stock price prediction using news sentiment analysis", In2019 IEEE fifth international conference on big data computing service and applications (BigDataService), pp. 205-208, 2019. [DOI:10.1109/BigDataService.2019.00035]
14. S. Negash, "Business intelligence", Communications of the association for information systems, vol. 13, no. 15, pp. 177-195, 2004. [DOI:10.17705/1CAIS.01315]
15. H. Chen, RHL. Chiang, VC. Storey, "Business intelligence and analytics: From big data to big impact", MIS quarterly, vol. , no. 1, pp. 1165-1188, 2012. [DOI:10.2307/41703503]
16. J. Park, V. Barash, C. Fink, M. Cha, "Emoticon style: Interpreting differences in emoticons across cultures", In Proceedings of the international AAAI conference on web and social media, vol. 7, no. 1, pp. 466-475, 2013. [DOI:10.1609/icwsm.v7i1.14437]
17. K. Spirovski, E. Stevanoska, A. Kulakov, "Comparison of different model's performances in task of document classification", In Proceedings of the 8th International Conference on Web Intelligence, Mining and Semantics, Novi Sad, Serbia, pp. 1-12, 2018. [DOI:10.1145/3227609.3227668] [PMID]
18. KS. Kyaw, P. Tepsongkroh, C. Thongkamkaew, "Business Intelligent Framework Using Sentiment Analysis for Smart Digital Marketing in the E-Commerce Era", Asia Social, vol. 16, no. 3, pp. e252965-e252965, 2023. [DOI:10.48048/asi.2023.252965]
19. D. Yan, K. Li, S. Gu, L. Yang, "Network-based bag-of-words model for text classification", IEEE Access, vol. 8, pp. 82641-82652, 2020. [DOI:10.1109/ACCESS.2020.2991074]
20. WA. Qader, MM. Ameen, "An overview of bag of words; importance, implementation, applications, and challenges", In2019 international engineering conference (IEC) , pp. 200-204, 2019. [DOI:10.1109/IEC47844.2019.8950616]
21. C. Niu, W. Zhang, S. Byna, Y. Chen, "Kv2vec: A Distributed Representation Method for Key-value Pairs from Metadata Attributes", IEEE High Performance Extreme Computing Conference (HPEC), pp. 1-7, 2022. [DOI:10.1109/HPEC55821.2022.9926389]
22. J. Cai, J. Luo, S. Wang, S. Yang, "Feature selection in machine learning: A new perspective", Neurocomputing, vol. 300, pp. 70-79, 2023. [DOI:10.1016/j.neucom.2017.11.077]
23. DH. Hubel, TN. Wiesel, "Receptive fields, binocular interaction and functional architecture in the cat's visual cortex", The Journal of physiology, vol. 160, no. 1, pp. 106-154, 1962. [DOI:10.1113/jphysiol.1962.sp006837] [PMID] []
24. A. Joulin, E. Grave, P. Bojanowski, M. Douze, "Fasttext. zip: Compressing text classification models", arXiv preprint, 2016.
25. P. Bojanowski, E. Grave, A. Joulin, "Enriching word vectors with subword information", Transactions of the association for computational linguistics, vol. 5, pp. 135-146, 2017. [DOI:10.1162/tacl_a_00051]
26. JL. Elman, "Finding structure in time", Cognitive Science, vol. 14, no. 2, pp. 179-211, 1990. [DOI:10.1016/0364-0213(90)90002-E]
27. S. Hochreiter, J. Schmidhuber, "Long short-term memory", Neural computation, vol. 9, no. 8, pp. 1735-1780, 1997. [DOI:10.1162/neco.1997.9.8.1735] [PMID]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
