A Sentiment Analysis Based Approach for Understanding the User Satisfaction on Android Application

The consistency of user satisfaction on mobile application has been more competitive because of the rapid growth of multi-featured applications. The analysis of user reviews or opinions can play a major role to understand the user’s emotions or demands. Several approaches in different areas of sentiment analysis have been proposed recently. The main objective of this work is to assist the developers in identifying the user’s opinion on their apps whether positive or negative. A sentiment analysis based approach has been proposed in this paper. NLP-based techniques Bags-of-Words, N-Gram, and TF-IDF along with Machine Learning Classifiers, namely, KNN, Random Forest (RF), SVM, Decision Tree, Naive Byes have been used to determine and generate a well-fitted model. It’s been found that RF provides 87.1% accuracy, 91.4% precision, 81.8% recall, 86.3% F1-Score. 88.9% of accuracy, 90.8% of precision, 86.4% of recall, and 88.5% of F1-Score are obtained from SVM.

[1]  Andrew H. Sung,et al.  Evaluation of Tree Based Machine Learning Classifiers for Android Malware Detection , 2018, ICCCI.

[2]  Saifee Vohra,et al.  Applications and Challenges for Sentiment Analysis : A Survey , 2013 .

[3]  Sheikh Shah Mohammad Motiur Rahman,et al.  StackDroid: Evaluation of a Multi-level Approach for Detecting the Malware on Android Using Stacked Generalization , 2018, RTIP2R.

[4]  P. V. G. D. Prasad Reddy,et al.  A survey of cross-domain text categorization techniques , 2012, 2012 1st International Conference on Recent Advances in Information Technology (RAIT).

[5]  Cane Leung,et al.  Sentiment Analysis of Product Reviews , 2009, Encyclopedia of Data Warehousing and Mining.

[6]  V. Smrithi Rekha,et al.  Recommending products to customers using opinion mining of online product reviews and features , 2015, 2015 International Conference on Circuits, Power and Computing Technologies [ICCPCT-2015].

[7]  Bing Liu,et al.  Mining Opinion Features in Customer Reviews , 2004, AAAI.

[8]  Walaa Medhat,et al.  Sentiment analysis algorithms and applications: A survey , 2014 .

[9]  Ankur Agrawal,et al.  Sentiment Analysis of Tweets to Gain Insights into the 2016 US Election , 2020 .

[10]  Sheikh Shah Mohammad Motiur Rahman,et al.  Supervised Ensemble Machine Learning Aided Performance Evaluation of Sentiment Classification , 2018, Journal of Physics: Conference Series.

[11]  Björn W. Schuller,et al.  Multimodal Bag-of-Words for Cross Domains Sentiment Analysis , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[12]  Rafael Muñoz,et al.  Ensemble classifier for Twitter sentiment analysis , 2015, WNACP@NLDB.

[13]  Goutam Sanyal,et al.  Performance Assessment of Multiple Classifiers Based on Ensemble Feature Selection Scheme for Sentiment Analysis , 2018, Appl. Comput. Intell. Soft Comput..

[14]  Madasu Hanmandlu,et al.  Zoning based Devanagari character recognition , 2011 .

[15]  Doaa Mohey El Din Mohamed Hussein,et al.  A survey on sentiment analysis challenges , 2016, Journal of King Saud University - Engineering Sciences.

[16]  Ram Mohana Reddy Guddeti,et al.  Performance analysis of Ensemble methods on Twitter sentiment analysis using NLP techniques , 2015, Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing (IEEE ICSC 2015).

[17]  Bing Liu,et al.  Sentiment Analysis and Subjectivity , 2010, Handbook of Natural Language Processing.

[18]  Yiming Yang,et al.  A re-examination of text categorization methods , 1999, SIGIR '99.

[19]  Murthy J.V.R,et al.  Text Document Classification based-on Least Square Support Vector Machines with Singular Value Decomposition , 2011 .