ارایه یک مدل هوشمند به‌منظور تشخیص چندوجهی شخصیت کاربران با استفاده از روش‌های یادگیری ژرف
محورهای موضوعی :
حسین صدر
1
,
فاطمه محدث دیلمی
2
,
مرتضی ترخان
3
1 - هیات علمی
2 - دانشجو
3 - دانشیار
کلید واژه: یادگیری ژرف, شبکه عصبی کانولوشنی, مدل ترکیب آدابوست, تشخیص شخصیت, داده‌های متنی.,
چکیده مقاله :
با توجه به رشد قابل‌توجه اطلاعات و داده‌های متنی که توسط انسان‌ها در شبکه‌های مجازی تولید می‌شوند، نیاز به سیستم‌هایی است که بتوان به کمک آن‌ها به‌صورت خودکار به تحلیل داده‌ها پرداخت و اطلاعات مختلفی را از آن‌ها استخراج کرد. یکی از مهم‌ترین داده‌های متنی موجود در سطح وب دید‌گاه‌های افراد نسبت به یک موضوع مشخص است. متن‌های منتشرشده توسط کاربران در فضای مجازی می‌تواند معرف شخصیت آن‌ها باشد. الگوریتم‌های یادگیری ماشین می‌تواند انتخاب مناسبی برای تجزیه‌و‌تحلیل این‌گونه مسائل باشند، اما به‌منظور غلبه بر پیچیدگی و پراکندگی محتوایی و نحوی داده‌ها نیاز به الگوریتم‌های یادگیری ژرف بیش از پیش در این حوزه احساس می‌شود. در این راستا، هدف این مقاله به‌کارگیری الگوریتم‌های یادگیری ژرف به‌منظور دسته‌بندی متون برای پیش‌بینی شخصیت می‌باشد. برای رسیدن به این هدف، شبکه عصبی کانولوشنی با مدل آدابوست به‌منظور دسته‌بندی داده‌ها ترکیب گردید تا بتوان به کمک آن داده‌های آزمایشی که با خطا دسته‌بندی شده‌اند را در مرحله دوم دسته‌بندی با اختصاص ضریب آلفا، با دقت بالاتری دسته‌بندی کرد. مدل پیشنهادی این مقاله روی دو مجموعه داده ایزیس و یوتیوب آزمایش شد و بر اساس نتایج بدست آمده مدل پیشنهادی از دقت بالاتری نسبت به سایر روش‌های موجود روی هر دو مجموعه داده برخودار است.
Due to the significant growth of textual information and data generated by humans on social networks, there is a need for systems that can automatically analyze the data and extract valuable information from them. One of the most important textual data is people's opinions about a particular topic that are expressed in the form of text. Text published by users on social networks can represent their personality. Although machine learning based methods can be considered as a good choice for analyzing these data, there is also a remarkable need for deep learning based methods to overcome the complexity and dispersion of content and syntax of textual data during the training process. In this regard, the purpose of this paper is to employ deep learning based methods for personality recognition. Accordingly, the convolutional neural network is combined with the Adaboost algorithm to consider the possibility of using the contribution of various filter lengths and gasp their potential in the final classification via combining various classifiers with respective filter sizes using AdaBoost. The proposed model was conducted on Essays and YouTube datasets. Based on the empirical results, the proposed model presented superior performance compared to other existing models on both datasets.
[1] N. Tsapatsoulis and C. Djouvas, "Opinion mining from social media short texts: Does collective intelligence beat deep learning?," Frontiers Robotics AI, 2019.
[2] H. Sadr, M. M. Pedram, and M. Teshnehlab, "Convolutional Neural Network Equipped with Attention Mechanism and Transfer Learning for Enhancing Performance of Sentiment Analysis," Journal of AI and Data Mining, pp. -, 2021, doi: 10.22044/jadm.2021.9618.2100.
[3] P. Chaiwuttisak, "Text Mining Analysis of Comments in Thai Language for Depression from Online Social Networks," in Soft Computing for Biomedical Applications and Related Topics: Springer, 2020, pp. 301-313.
[4] H. Sadr, M. M. Pedram, and M. Teshnelab, "Improving the Performance of Text Sentiment Analysis using Deep Convolutional Neural Network Integrated with Hierarchical Attention Layer," International Journal of Information and Communication Technology Research, vol. 11, no. 3, pp. 57-67, 2019.
[5] J. A. Golbeck, "Predicting personality from social media text," AIS Transactions on Replication Research, vol. 2, no. 1, p. 2, 2016.
[6] H. Sadr, M. N. Solimandarabi, M. M. Pedram, and M. Teshnehlab, "A Novel Deep Learning Method for Textual Sentiment Analysis," arXiv preprint arXiv:2102.11651, 2021.
[7] D. Schultz and S. E. Schultz, Psychology and Work Today: Pearson New International Edition CourseSmart eTextbook. Routledge, 2015.
[8] A. H. Jadidinejad and H. Sadr, "Improving weak queries using local cluster analysis as a preliminary framework," Indian Journal of Science and Technology, vol. 8, no. 5, pp. 495-510, 2015.
[9] G. W. Allport, "Personality: A psychological interpretation," 1937.
[10] R. S. Camati and F. Enembreck, "Text-Based Automatic Personality Recognition: a Projective Approach," in 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2020: IEEE, pp. 218-225.
[11] H. Sadr, M. N. Soleimandarabi, M. Pedram, and M. Teshnelab, "Unified Topic-Based Semantic Models: A Study in Computing the Semantic Relatedness of Geographic Terms," in 2019 5th International Conference on Web Research (ICWR), 2019: IEEE, pp. 134-140.
[12] D. Xue et al., "Deep learning-based personality recognition from text posts of online social networks," Applied Intelligence, vol. 48, no. 11, pp. 4232-4246, 2018.
[13] Y. Mehta, N. Majumder, A. Gelbukh, and E. Cambria, "Recent trends in deep learning based personality detection," Artificial Intelligence Review, pp. 1-27, 2019.
[14] H. Sadr, M. M. Pedram, and M. Teshnehlab, "A Robust Sentiment Analysis Method Based on Sequential Combination of Convolutional and Recursive Neural Networks," Neural Processing Letters, pp. 1-17, 2019.
[15] H. Sadr, M. M. Pedram, and M. Teshnehlab, "Multi-View Deep Network: A Deep Model Based on Learning Features From Heterogeneous Neural Networks for Sentiment Analysis," IEEE Access, vol. 8, pp. 86984-86997, 2020.
[16] A. Remaida, B. Abdellaoui, A. Moumen, and Y. E. B. El Idrissi, "Personality traits analysis using Artificial Neural Networks: A Literature Survey," in 2020 1st International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), 2020: IEEE, pp. 1-6.
[17] H. Sadr, M. Nazari Solimandarabi, and M. Mirhosseini Moghadam, "Categorization of Persian Detached Handwritten Letters Using Intelligent Combinations of Classifiers," Journal of Advances in Computer Research, vol. 8, no. 4, pp. 13-21, 2017.
[18] H. Sadr and M. Nazari Solimandarabi, "Presentation of an efficient automatic short answer grading model based on combination of pseudo relevance feedback and semantic relatedness measures," Journal of Advances in Computer Research, vol. 10, no. 2, pp. 1-10, 2019.
[19] H. Sadr, M. Nazari, M. M. Pedram, and M. Teshnehlab, "Exploring the Efficiency of Topic-Based Models in Computing Semantic Relatedness of Geographic Terms," International Journal of Web Research, vol. 2, no. 2, pp. 23-35, 2019.
[20] H. Sadr, R. Atani, and M. Yamaghani, "The Significance of Normalization Factor of Documents to Enhance the Quality of Search in Information Retrieval Systems," International Journal of Computer Science and Network Solutions, vol. 2, no. 5, pp. 91-97, 2014.
[21] J. Golbeck, C. Robles, M. Edmondson, and K. Turner, "Predicting personality from twitter," in 2011 IEEE third international conference on privacy, security, risk and trust and 2011 IEEE third international conference on social computing, 2011: IEEE, pp. 149-156.
[22] D. Quercia, M. Kosinski, D. Stillwell, and J. Crowcroft, "Our twitter profiles, our selves: Predicting personality with twitter," in 2011 IEEE third international conference on privacy, security, risk and trust and 2011 IEEE third international conference on social computing, 2011: IEEE, pp. 180-185.
[23] F. Alam, E. A. Stepanov, and G. Riccardi, "Personality traits recognition on social network-facebook," in Seventh International AAAI Conference on Weblogs and Social Media, 2013.
[24] M. Skowron, M. Tkalčič, B. Ferwerda, and M. Schedl, "Fusing social media cues: personality prediction from twitter and instagram," in Proceedings of the 25th international conference companion on world wide web, 2016, pp. 107-108.
[25] D. Xue et al., "Personality recognition on social media with label distribution learning," IEEE Access, vol. 5, pp. 13478-13488, 2017.
[26] E. Tighe and C. Cheng, "Modeling personality traits of filipino twitter users," in Proceedings of the Second Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media, 2018, pp. 112-122.
[27] H.-C. Yang and Z.-R. Huang, "Mining personality traits from social messages for game recommender systems," Knowledge-Based Systems, vol. 165, pp. 157-168, 2019.
[28] S. Han, H. Huang, and Y. Tang, "Knowledge of words: An interpretable approach for personality recognition from social media," Knowledge-Based Systems, p. 105550, 2020.
[29] J. Yu and K. Markov, "Deep learning based personality recognition from facebook status updates," in 2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST), 2017: IEEE, pp. 383-387.
[30] T. Tandera, D. Suhartono, R. Wongso, and Y. L. Prasetio, "Personality prediction system from facebook users," Procedia computer science, vol. 116, pp. 604-611, 2017.
[31] B. B. C. da Silva and I. Paraboni, "Personality recognition from Facebook text," in International Conference on Computational Processing of the Portuguese Language, 2018: Springer, pp. 107-114.
[32] Z. Wang, C.-H. Wu, Q.-B. Li, B. Yan, and K.-F. Zheng, "Encoding Text Information with Graph Convolutional Networks for Personality Recognition," Applied Sciences, vol. 10, no. 12, p. 4081, 2020.
[33] E. A. Rissola, S. A. Bahrainian, and F. Crestani, "Personality recognition in conversations using capsule neural networks," in IEEE/WIC/ACM International Conference on Web Intelligence, 2019, pp. 180-187.
[34] N. Majumder, S. Poria, A. Gelbukh, and E. Cambria, "Deep learning-based document modeling for personality detection from text," IEEE Intelligent Systems, vol. 32, no. 2, pp. 74-79, 2017.
[35] S. M. Mohammad and S. Kiritchenko, "Using hashtags to capture fine emotion categories from tweets," Computational Intelligence, vol. 31, no. 2, pp. 301-326, 2015.
[36] X. Sun, B. Liu, J. Cao, J. Luo, and X. Shen, "Who am I? Personality detection based on deep learning for texts," in 2018 IEEE International Conference on Communications (ICC), 2018: IEEE, pp. 1-6.
[37] Y. Freund, "An adaptive version of the boost by majority algorithm," Machine learning, vol. 43, no. 3, pp. 293-318, 2001.
[38] T. Young, D. Hazarika, S. Poria, and E. Cambria, "Recent trends in deep learning based natural language processing," ieee Computational intelligenCe magazine, vol. 13, no. 3, pp. 55-75, 2018.
[39] T. Mikolov, K. Chen, G. Corrado, and J. Dean, "Efficient estimation of word representations in vector space," arXiv preprint arXiv:1301.3781, 2013.
[40] T. Mikolov, K. Chen, G. Corrado, and J. Dean, "Distributed Representations of Words and Phrases and their Compositionality, Nips," 2013.
[41] I. Goodfellow, Y. Bengio, A. Courville, and Y. Bengio, Deep learning. MIT press Cambridge, 2016.
[42] T. Young, D. Hazarika, S. Poria, and E. Cambria, "Recent trends in deep learning based natural language processing," arXiv preprint arXiv:1708.02709, 2017.
[43] O. Irsoy and C. Cardie, "Deep recursive neural networks for compositionality in language," in Advances in neural information processing systems, 2014, pp. 2096-2104.
[44] Y. Zhang and B. Wallace, "A sensitivity analysis of (and practitioners' guide to) convolutional neural networks for sentence classification," arXiv preprint arXiv:1510.03820, 2015.
[45] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436-444, May, 2015.
[46] J. W. Pennebaker and L. A. King, "Linguistic styles: Language use as an individual difference," Journal of personality and social psychology, vol. 77, no. 6, p. 1296, 1999.
[47] J.-I. Biel, V. Tsiminaki, J. Dines, and D. Gatica-Perez, "Hi YouTube! Personality impressions and verbal content in social video," in Proceedings of the 15th ACM on International conference on multimodal interaction, 2013, pp. 119-126.
An Intelligent Model for Multidimensional Personality Recognition of Users using Deep Learning Methods
Abstract:
Due to the significant growth of textual information and data generated by humans on social networks, there is a need for systems that can automatically analyze the data and extract valuable information from them. One of the most important textual data is people's opinions about a particular topic that are expressed in the form of text. Text published by users on social networks can represent their personality. Although machine learning based methods can be considered as a good choice for analyzing these data, there is also a remarkable need for deep learning based methods to overcome the complexity and dispersion of content and syntax of textual data during the training process. In this regard, the purpose of this paper is to employ deep learning based methods for personality recognition. Accordingly, the convolutional neural network is combined with the Adaboost algorithm to consider the possibility of using the contribution of various filter lengths and gasp their potential in the final classification via combining various classifiers with respective filter sizes using AdaBoost. The proposed model was conducted on Essays and YouTube datasets. Based on the empirical results, the proposed model presented superior performance compared to other existing models on both datasets.
Keywords: Deep learning, Convolutional neural network, Adaboost combinational model, Personality recognition, Textual data
