یک مدل تشخیص احساسات معنایی مبتنی بر آنتولوژی و آتوماتای یادگیر عمیق سلولی
محورهای موضوعی : تخصصی
هوشنگ صالحی
1
,
رضا قائمی
2
,
مریم خیرآبادی
3
1 - گروه مهندسی کامپیوتر، واحد نیشابور، دانشگاه آزاد اسلامی، نیشابور، ایران
2 - گروه مهندسی کامپیوتر، واحد قوچان، دانشگاه آزاد اسلامی، قوچان، ایران
3 - گروه مهندسی کامپیوتر، واحد نیشابور، دانشگاه آزاد اسلامی، نیشابور، ایران
کلید واژه: نظر کاوی, تحلیل احساسات, شبکه عصبی عمیق, آتوماتای سلولی, آنتولوژی,
چکیده مقاله :
امروزه شبکه های اجتماعی و رسانه های ارتباطی نقش به سزایی را در زندگی روزمره کاربران دارند. کاربران در زمینه های مختلف در شبکه های اجتماعی اقدام به گفتگو و تبادل اطلاعات می نمایند. در جملات و کامنت های کاربران احساسات منفی و مثبت در رابطه با اخبار روز، اتفاقات موجود و غیره وجود دارد که تشخیص این احساسات با چالش های زیادی مواجه است. تاکنون روش های مختلفی مانند یادگیری ماشین، رویکردهای آماری، هوش مصنوعی و غیره به منظور تشخیص احساسات مطرح شده است که علی رغم کاربردهای فراوانی که داشته اند؛ اما هنوز نتوانسته دقت، شفافیت و صحت قابل قبولی داشته باشند. بنابراین در این مقاله، یک مدل نظرکاوی معنایی مبتنی بر آنتولوژی با استفاده از آتوماتای یادگیر عمیق سلولی مبتنی بر شبکه عصبی عمیق GMDH ارائه شده است. از رویکرد آنتولوژی برای انتخاب ویژگی های برجسته مبتنی بر قوانین تولید و از آتوماتای یادگیر عمیق سلولی برای طبقه بندی احساسات کاربران استفاده می‌‌شود. نوآوری اصلی این مقاله الگوریتم پیشنهادی آن است که یک روش یادگیری عمیق جهت پردازش تنها یک عبارت توسعه داده شده و سپس با انتقال آن به حوزه آتوماتای سلولی، پردازش موازی و یا توزیع شده آن فراهم می شود. در این مقاله، از مجموعه داده های مشتریان آمازون، توئیتر، فیس بوک، اخبار جعلی COVID-19، آمازون و شبکه اخبار جعلی استفاده شده است. با شبیه سازی روش پیشنهادی مشاهده گردید که روش پیشنهادی نسبت به سایر روش های دیگر به طور میانگین 3% بهبود داشته است
Today, social networks and communication media play a significant role in the daily life of users. Users talk and exchange information in different fields in social networks. In the sentences and comments of users, there are negative and positive feelings in relation to the news of the day, current events, etc., and recognizing these feelings faces many challenges. So far, various methods such as machine learning, statistical approaches, artificial intelligence, etc., have been proposed for the purpose of detecting emotions, which despite their many applications; But they have not yet been able to have acceptable accuracy, transparency and accuracy. Therefore, in this article, an ontology-based semantic analysis model using cellular deep learning automata based on GMDH deep neural network is presented. Ontology approach is used to select salient features based on production rules and cellular deep learning automata is used to classify user sentiments. The main innovation of this article is the proposed algorithm that a deep learning method is developed to process only one expression and then by transferring it to the field of cellular automata, parallel or distributed processing is provided. In this article, the data sets of Amazon customers, Twitter, Facebook, fake news of COVID-19, Amazon and fake news network are used. By simulating the proposed method, it was observed that the proposed method has an average improvement of 3% compared to other methods
[1] Yoo, S., Song, J., & Jeong, O. (2018). Social media contents-based sentiment analysis and prediction system. Expert Systems with Applications, 105, 102-111.
[2] Liu, B. (2020). Text sentiment analysis based on CBOW model and deep learning in big data environment. Journal of ambient intelligence and humanized computing, 11(2), 451-458.
[3] Singh, N. K., Tomar, D. S., & Sangaiah, A. K. (2020). Sentiment analysis: a review and comparative analysis over social media. Journal of Ambient Intelligence and Humanized Computing, 11(1), 97-117.
[4] Mandloi, L., & Patel, R. (2020, June). Twitter sentiments analysis using machine learninig methods. In 2020 International Conference for Emerging Technology (INCET) (pp. 1-5). IEEE.
[5] Chen, L. C., Lee, C. M., & Chen, M. Y. (2020). Exploration of social media for sentiment analysis using deep learning. Soft Computing, 24(11), 8187-8197.
[6] Chauhan, U. A., Afzal, M. T., Shahid, A., Abdar, M., Basiri, M. E., & Zhou, X. (2020). A comprehensive analysis of adverb types for mining user sentiments on amazon product reviews. World Wide Web, 23(3), 1811-1829.
[7] Behera, R. K., Jena, M., Rath, S. K., & Misra, S. (2021). Co-LSTM: Convolutional LSTM model for sentiment analysis in social big data. Information Processing & Management, 58(1), 102435.
[8] Chandra, S., Gourisaria, M. K., Harshvardhan, G. M., Rautaray, S. S., Pandey, M., & Mohanty, S. N. (2021). Semantic Analysis of Sentiments through Web-Mined Twitter Corpus. In ISIC (pp. 122-135).
[9] Pathak, A. R., Pandey, M., & Rautaray, S. (2021). Topic-level sentiment analysis of social media data using deep learning. Applied Soft Computing, 108, 107440.
[10] Awajan, I., Mohamad, M., & Al-Quran, A. (2021). Sentiment analysis technique and neutrosophic set theory for mining and ranking big data from online reviews. IEEE Access, 9, 47338-47353.
[11] Cai, Y., Ke, W., Cui, E., & Yu, F. (2022). A deep recommendation model of cross-grained sentiments of user reviews and ratings. Information Processing & Management, 59(2), 102842.
[12] Revathy, G., Alghamdi, S. A., Alahmari, S. M., Yonbawi, S. R., Kumar, A., & Haq, M. A. (2022). Sentiment analysis using machine learning: Progress in the machine intelligence for data science. Sustainable Energy Technologies and Assessments, 53, 102557.
[13] Biradar, S. H., Gorabal, J. V., & Gupta, G. (2022). Machine learning tool for exploring sentiment analysis on twitter data. Materials Today: Proceedings, 56, 1927-1934.
[14] Villegas-Ch, W., Molina, S., Janón, V. D., Montalvo, E., & Mera-Navarrete, A. (2022, August). Proposal of a Method for the Analysis of Sentiments in Social Networks with the Use of R. In Informatics (Vol. 9, No. 3, p. 63). MDPI.
[15] Jain, D. K., Boyapati, P., Venkatesh, J., & Prakash, M. (2022). An intelligent cognitive-inspired computing with big data analytics framework for sentiment analysis and classification. Information Processing & Management, 59(1), 102758.
[16]
Ali, F., Kwak, D., Khan, P., Islam, S. R., Kim, K. H., & Kwak, K. S. (2017). Fuzzy ontology-based sentiment analysis of transportation and city feature reviews for safe traveling. Transportation Research Part C: Emerging Technologies, 77, 33-48.
[17] Alarifi, A., Tolba, A., Al-Makhadmeh, Z., & Said, W. (2020). A big data approach to sentiment analysis using greedy feature selection with cat swarm optimization-based long short-term memory neural networks. The Journal of Supercomputing, 76(6), 4414-4429.
[18] https://www.kaggle.com/datasets/kazanova/sentiment140.
[19] https://www.kaggle.com/datasets/techykajal/fakereal-news.
[20] https://www.kaggle.com/datasets/elvinagammed/covid19-fake-news-dataset-nlp.
[21] https://www.kaggle.com/datasets/marklvl/sentiment-labelled-sentences-data-set.
[22] https://www.kaggle.com/datasets/mdepak/fakenewsnet.
[23] Guo, H., Li, S., Qi, K., Guo, Y., & Xu, Z. (2018). Learning automata-based competition scheme to train deep neural networks. IEEE Transactions on Emerging Topics in Computational Intelligence, 4(2), 151-158.
[24] Hossin, M., & Sulaiman, M. N. (2015). A review on evaluation metrics for data classification evaluations. International journal of data mining & knowledge management process, 5(2), 1.
[25] Gilpin, W. (2019). Cellular automata as convolutional neural networks. Physical Review E, 100(3), 032402.
[26] Ivakhnenko, A. G. (1971). Polynomial theory of complex systems. IEEE transactions on Systems, Man, and Cybernetics, (4), 364-378.
[27] Farlow, S. J. (1984). Self-Organizing Method in Modeling: GMDH. Type Algorithm.
[28] Nariman-Zadeh, N., Darvizeh, A., & Ahmad-Zadeh, G. R. (2003). Hybrid genetic design of GMDH-type neural networks using singular value decomposition for modelling and prediction of the explosive cutting process. Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 217(6), 779-790.
[29] Nariman-Zadeh, N., DARVIZEH, A., & DARVIZEH, M. (2001). GMDH-Type Neural Network Modelling of Explosive Welding Process of Plates Using Singular Value Decomposition.
[30] Nariman-Zadeh, N., Darvizeh, A., Darvizeh, M., & Gharababaei, H. (2002). Modelling of explosive cutting process of plates using GMDH-type neural network and singular value decomposition. Journal of Materials Processing Technology, 128(1-3), 80-87.
[31] Mahendhiran, P. D., & Subramanian, K. (2022). CLSA-CapsNet: Dependency based concept level sentiment analysis for text. Journal of Intelligent & Fuzzy Systems, (Preprint), 1-17.
[32] Mandloi, L., & Patel, R. (2020, June). Twitter sentiments analysis using machine learninig methods. In 2020 International Conference for Emerging Technology (INCET) (pp. 1-5). IEEE.
[33] Pathak, A. R., Pandey, M., & Rautaray, S. (2021). Topic-level sentiment analysis of social media data using deep learning. Applied Soft Computing, 108, 107440.
[34] Revathy, G., Alghamdi, S. A., Alahmari, S. M., Yonbawi, S. R., Kumar, A., & Haq, M. A. (2022). Sentiment analysis using machine learning: Progress in the machine intelligence for data science. Sustainable Energy Technologies and Assessments, 53, 102557.
[35] Singh, N. K., Tomar, D. S., & Sangaiah, A. K. (2020). Sentiment analysis: a review and comparative analysis over social media. Journal of Ambient Intelligence and Humanized Computing, 11(1), 97-117.
[36] Villegas-Ch, W., Molina, S., Janón, V. D., Montalvo, E., & Mera-Navarrete, A. (2022, August). Proposal of a Method for the Analysis of Sentiments in Social Networks with the Use of R. In Informatics (Vol. 9, No. 3, p. 63). MDPI.
[37] Yoo, S., Song, J., & Jeong, O. (2018). Social media contents-based sentiment analysis and prediction system. Expert Systems with Applications, 105, 102-111.
[38] Yue, L., Chen, W., Li, X., Zuo, W., & Yin, M. (2019). A survey of sentiment analysis in social media. Knowledge and Information Systems, 60(2), 617-663.
[39] Zong, C., Xia, R., & Zhang, J. (2021). Sentiment analysis and opinion mining. In Text Data Mining (pp. 163-199). Springer, Singapore.
[40] Maity, D., Kanakaraddi, S., & Giraddi, S. (2023). Text Sentiment Analysis based on Multichannel Convolutional Neural Networks and Syntactic Structure. Procedia Computer Science, 218, 220-226.
[41] Sodhar, I. N., Sulaiman, S., Buller, A. H., & Sodhar, A. N. (2023). Hybrid Approach Used to Analyze the Sentiments of Romanized Text (Sindhi). International Journal of Advanced Computer Science and Applications, 14(3).
[42] Fazal, U., Khan, M., Maqbool, M. S., Bibi, H., & Nazeer, R. (2023). Sentiment Analysis of Omicron Tweets by using Machine Learning Models
