بهبود تعیین قطبیت جمله در تحلیل احساسات مبتنی بر الگوریتم یادگیری عمیق RNN و LSTM

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی کارشناسی ارشد گروه مهندسی کامپیوتر- واحد یزد- دانشگاه آزاد اسلامی- یزد- ایران

2 دانشکده فنی و مهندسی، گروه مهندسی کامپیوتر، دانشگاه آزاد اسلامی واحد یزد

چکیده

امروزه به دلیل وجود حجم انبوه نظرات منتشرشده توسط افراد در فضای مجازی، تحلیل احساسات نقش اساسی را در استخراج اطلاعات بازی می-کند. یکی از تکنیکهای نوین براساس مطالعات انجام‌شده به منظور تعیین دقیق‌تر قطبیت جمله در تحلیل احساسات مبتنی بر الگوریتم‌های یادگیری عمیق است. در این تحقیق به منظور تعیین قطبیت نظرات متنی از الگوریتم یادگیری عمیق LSTM و RNN استفاده شده‌است تا با بررسی و مقایسه این دو الگوریتم بتوان الگوریتم مناسب برای تحلیل احساسات را انتخاب نمود. همچنین در روش پیشنهادی برای تعیین روابط معنایی بین کلمات از روش تعبیه‌گذاری کلمات از پیش آموزش داده‌شده‌ی Wordtovec استفاده‌شد تا دقت روش پیشنهادی افزایش یابد. روش پیشنهادی بر روی دو مجموعه داده airline-tweet و IMDB ارزیابی شد. نتایج ارزیابی نشان می‌دهد که روش پیشنهادی بر روی مجموعه داده airline-tweet در صورت استفاده از تعبیه‌گذاری Wordtovec دقت 78/0 دارد. همچنین روش پیشنهادی بر روی مجموعه داده IMDB در صورت استفاده از تعبیه‌گذاری Wordtovec دقت 84/0 دارد.

کلیدواژه‌ها


عنوان مقاله [English]

Improving Sentence Polarity Determination In Sentiment Analysis based on RNN and LSTM Deep Learning Algorithm

نویسندگان [English]

  • Narjes chavosh 1
  • Sima Emadi 2
1 Master student of computer engineering department - Yazd branch - Islamic Azad University. Iran
2 Assistant Professor, Department of Computer Engineering, Yazd Branch, Islamic Azad University, Yazd, Iran
چکیده [English]

Today, due to the large volume of opinions published by people in cyberspace, sentiment analysis plays a key role in extracting information. One of the new techniques based on studies has been done to determine the exact polarity of the sentence in sentiment analysis is deep learning algorithms. In this research, two deep learning algorithms, namely RNN and LSTM, has been used to determine sentence polarity in order to achieve more accurate results. Moreover, in the proposed technique, pre-trained word embedding algorithm, namely Wordtovec, was used to determine the semantic relationships between words to increase the accuracy of the proposed method. The proposed method was evaluated on two data sets; airline-tweet and IMDB. The evaluation results show that on the airline-tweet dataset, the proposed method has an accuracy of 0.78 and accuracy of 0.84 on the IMDB data set.

کلیدواژه‌ها [English]

  • Sentiment Analysis
  • Deep Learning
  • RNN
  • LSTM
  • Word Embedding
  • Word2vec
[1] M., Huang, Q., Qian, X., Zhu, "Encoding syntactic knowledge in neural networks for sentiment classification", ACM Transactions on Information Systems (TOIS),Vol. 35, no. 3,  2017 Jun.
[2] H., Jiang, F., Qin, J., Cao, Y., Peng, Y., Shao, "Recurrent neural network from adder’s perspective: Carry-lookahead RNN", Neural Networks, Vol. 144, P. 297-306, 2021 Dec.
[3] Y., Zhang, J., Wang, X., Zhang, "Conciseness is better: Recurrent attention LSTM model for document-level sentiment analysis", Neurocomputing, Vol. 462, P. 101-12, 2021 Oct.
[4] A., Abdi, SM., Shamsuddin, S. Hasan, J., Piran. "Deep learning-based sentiment classification of evaluative text based on Multi-feature fusion", Information Processing & Management, Vol. 56, no. 4, P. 1245-59, 2019 Jul.
[5] D., Jatnika, MA., Bijaksana, AA., Suryani, "Word2vec model analysis for semantic similarities in english words", Procedia Computer Science, P. 160-7, 2019 Jan
 
[6] Y., Kim, "Convolutional neural networks for sentence classification", Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, P. 1746–1751, 2014
 
[7] N., Kalchbrenner, E., Grefenstette, P. Blunsom, "A convolutional neural network for modelling sentences", arXiv preprint arXiv:1404.2188. 2014 Apr 8.
 
[8] Z., Guan, L., Chen, W., Zhao, Y., Zheng, S., Tan, D., Cai, "Weakly-Supervised Deep Learning for Customer Review Sentiment Classification", IJCAI, p. 3719-3725, 2016 Jul 9.
 
[9] AS., Zharmagambetov, AA., Pak, "Sentiment analysis of a document using deep learning approach and decision trees", Twelve IEEE international conference on electronics computer and computation (ICECCO), p. 1-4, 2015 Sep 27.
 
[10] A., Mousa, B., Schuller, "Contextual bidirectional long short-term memory recurrent neural network language models: A generative approach to sentiment analysis", Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics", P. 1023–1032, 2017.
 
[11] Z., Teng, DT., Vo, Y. Zhang, "Context-sensitive lexicon features for neural sentiment analysis", Proceedings of the conference on empirical methods in natural language processing,  p. 1629-1638, 2016 Nov.
 
[12] Q., Qian, M., Huang, J., Lei, X., Zhu, "Linguistically regularized LSTMs for sentiment classification", arXiv preprint arXiv:1611.03949. 2016 Nov 12.
 
[13] X., Wang, W., Jiang, Z., Luo, "Combination of convolutional and recurrent neural network for sentiment analysis of short texts", Proceedings of the 26th international conference on computational linguistics: Technical papers, p. 2428-2437, 2016 Dec.
 
[14] C, Guggilla, T., Miller, I., Gurevych, "CNN-and LSTM-based claim classification in online user comments", Proceedings of the 26th international conference on computational linguistics: technical papers p. 2740-2751, 2016 Dec.
[15] Mohammdi, Rezaeian, Pazhohan, “Determine the polarity of users' opinions and identify requests with the help of deep learning techniques in Telegram”, Fourth National Conference on Applied Research in Electrical Engineering, Mechanics, Computers and Information Technology, Shiraz University, 2018. (in persian)
[16] R., Monika, S., Deivalakshmi, B., Janet, "Sentiment analysis of US airlines tweets using LSTM/RNN", IEEE 9th International Conference on Advanced Computing (IACC), p. 92-95, 2019 Dec.
[17] KN., Singh, SD., Devi, HM., Devi, AK., Mahanta, "A novel approach for dimension reduction using word embedding: An enhanced text classification approach", International Journal of Information Management Data Insights. Vol. 2, no. 1, 2022 Apr.
 
[18] J., Schmidhuber, "Deep learning in neural networks: An overview", Neural networks, Vol. 61, P. 85-117, 2015 Jan.