A COMBINED DEEP LEARNING MODEL FOR PERSIAN SENTIMENT ANALYSIS

With increasing members in social media sites today, people tend to share their views about everything online. It is a convenient way to convey their messages to end users on a specific subject. Sentiment Analysis is a subfield of Natural Language Processing (NLP) that refers to the identification of users’ opinions toward specific topics. It is used in several fields such as marketing, customer services, etc. However, limited works have been done on Persian Sentiment Analysis. On the other hand, deep learning has recently become popular because of its successful role in several Natural Language Processing tasks. The objective of this paper is to propose a novel hybrid deep learning architecture for Persian Sentiment Analysis. According to the proposed model, local features are extracted by Convolutional Neural Networks (CNN) and long-term dependencies are learned by Long Short Term Memory (LSTM). Therefore, the model can harness both CNN's and LSTM's abilities. Furthermore, Word2vec is used for word representation as an unsupervised learning step. To the best of our knowledge, this is the first attempt where a hybrid deep learning model is used for Persian Sentiment Analysis. We evaluate the model on a Persian dataset that is introduced in this study. The experimental results show the effectiveness of the proposed model with an accuracy of 85%. ABSTRAK: Hari ini dengan ahli yang semakin meningkat di laman media sosial, orang cenderung untuk berkongsi pandangan mereka tentang segala-galanya dalam talian. Ini adalah cara mudah untuk menyampaikan mesej mereka kepada pengguna akhir mengenai subjek tertentu. Analisis Sentimen adalah subfield Pemprosesan Bahasa Semula Jadi yang merujuk kepada pengenalan pendapat pengguna ke arah topik tertentu. Ia digunakan dalam beberapa bidang seperti pemasaran, perkhidmatan pelanggan, dan sebagainya. Walau bagaimanapun, kerja-kerja terhad telah dilakukan ke atas Analisis Sentimen Parsi. Sebaliknya, pembelajaran mendalam baru menjadi popular kerana peranannya yang berjaya dalam beberapa tugas Pemprosesan Bahasa Asli (NLP). Objektif makalah ini adalah mencadangkan senibina pembelajaran hibrid yang baru dalam Analisis Sentimen Parsi. Menurut model yang dicadangkan, ciri-ciri tempatan ditangkap oleh Rangkaian Neural Convolutional (CNN) dan ketergantungan jangka panjang dipelajari oleh Long Short Term Memory (LSTM). Oleh itu, model boleh memanfaatkan kebolehan CNN dan LSTM. Selain itu, Word2vec digunakan untuk perwakilan perkataan sebagai langkah pembelajaran tanpa pengawasan. Untuk pengetahuan yang terbaik, ini adalah percubaan pertama di mana model pembelajaran mendalam hibrid digunakan untuk Analisis Sentimen Persia. Kami menilai model pada dataset Persia yang memperkenalkan dalam kajian ini. Keputusan eksperimen menunjukkan keberkesanan model yang dicadangkan dengan ketepatan 85%.

[1]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[2]  Alimardani Saeedeh,et al.  OPINION MINING IN PERSIAN LANGUAGE USING SUPERVISED ALGORITHMS , 2015 .

[3]  Christopher Potts,et al.  Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank , 2013, EMNLP.

[4]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[5]  Muhammad Usman,et al.  An effective model for aspect based opinion mining for social reviews , 2015, 2015 Tenth International Conference on Digital Information Management (ICDIM).

[6]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[7]  Jeffrey Pennington,et al.  Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions , 2011, EMNLP.

[8]  Christopher Potts,et al.  Learning Word Vectors for Sentiment Analysis , 2011, ACL.

[9]  Andrew Y. Ng,et al.  Semantic Compositionality through Recursive Matrix-Vector Spaces , 2012, EMNLP.

[10]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[11]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[12]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[13]  Mohammad Rahmati,et al.  Sentiment analysis using deep learning on Persian texts , 2017, 2017 Iranian Conference on Electrical Engineering (ICEE).

[14]  Roliana Ibrahim,et al.  A SVM-based method for sentiment analysis in Persian language , 2013, International Conference on Graphic and Image Processing.

[15]  Reza Zafarani,et al.  Sarcasm Detection on Twitter: A Behavioral Modeling Approach , 2015, WSDM.

[16]  Ayoub Bagheri,et al.  Sentiment classification in Persian: Introducing a mutual information-based method for feature selection , 2013, 2013 21st Iranian Conference on Electrical Engineering (ICEE).

[17]  Mohammad Ehsan Basiri,et al.  Sentence-level sentiment analysis in Persian , 2017, 2017 3rd International Conference on Pattern Recognition and Image Analysis (IPRIA).

[18]  Chetan Agrawal,et al.  A Survey on Sentiment Analysis and Opinion Mining: A need for an Organization and Requirement of a customer , 2014 .

[19]  Bo Pang,et al.  Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[20]  Ronen Feldman,et al.  Techniques and applications for sentiment analysis , 2013, CACM.

[21]  Christopher D. Manning,et al.  Baselines and Bigrams: Simple, Good Sentiment and Topic Classification , 2012, ACL.

[22]  Lukás Burget,et al.  Recurrent neural network based language model , 2010, INTERSPEECH.