Sentiment analysis on mobile phones reviews | |
| Author | Jithender, Sakshi |
| Call Number | AIT RSPR no.ICT-20-06 |
| Subject(s) | Natural language processing (Computer science) Data mining Mobile communication systems |
| Note | A research submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Information and Communication Technologies, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Research studies project report ; no. ICT-20-06 |
| Abstract | In the present generation the consumer reviews serve as analysis for businesses in terms of product quality, performance, new features, to bring in desired changes and post sales customer services. In this research study, we forecast consumer outlook based on mobile phone reviews, along with providing an analysis of the major important factors behind reviews actually being classified as either positive or negative. This perception could help companies develop their products for capturing future market share together with helping the prospective buyers to make the right selection in buying the best reviewed brand and product model. This online e-commerce market for mobile phones have transformed the way we purchase products online by making all the information accessible at our fingertips. The research study is on Amazon Mobile Phones reviews which was carried out by, data cleaning, data pre-processing, removal of stop words, before converting the text to vector representation by applying a variety of feature extraction techniques such as bag-of-words(BOW), TF-IDF, and word2vec. The prime obejctive behind word embeddings is to remodel each word to a mathematical vector. We study the performance of distinct machine learning algorithms, such as K-Nearest Neighbor, Logistic Regression, Gradient Boosting and Random Forest. Furthermore, we evaluate these algorithms using accuracy, precision, recall, and F1-score. Additionally, we apply Tf-Idf technique to provide analytical reasons for the reviews being classified as either positive or negative. The study undertakes the sentiment analysis by consumers on Amazon e-commerce portal where each review is about the brand, model, camera, battery, dual SIM, price, storage capacity, processing speed and post purchasing the customer service. The study as accomplished brand wise positive / negative reviews thus provides the consumer’s with systematically shortlisted options to enable correct decision to purchase the most popular brand of mobile phones with latest features. The research study is concluded with a comprehensive tool of the Web Browser Application which is built on the proposed model to provide an inclusive view of the sentiment polarity on a real time basis. |
| Year | 2020 |
| Corresponding Series Added Entry | Asian Institute of Technology. Research studies project report ; no. ICT-20-06 |
| Type | Research Study Project Report (RSPR) |
| School | School of Engineering and Technology (SET) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Information and Communication Technology (ICT) |
| Chairperson(s) | Vatcharaporn Esichaikul; |
| Examination Committee(s) | Attaphongse Taparugssanagorn;Teerapat Sanguankotchakorn; |
| Scholarship Donor(s) | Asian Institute of Technology Fellowship; |
| Degree | Research Studies Project Report (M. Eng.) - Asian Institute of Technology, 2020 |