Feature-Based Mobile Phone Rating Using Sentiment Analysis and Machine Learning Approaches

Abstract

This project proposes a model of sentiment analysis of different features of different company's mobile sets and rating them overall. Customers before buying a phone check reviews to get a better understanding of the device and this project derives an optimum solution for this. In this model, every feature of a mobile phone is rated based on public opinion and an overall rating for every type. Amazon is one of the largest internet retailer, which makes way for most public reviews on their products and so we collected data for sentiment analysis from amazon. We pre-processed the gathered data to a supervised form and chose the most common features from train data. In our model, Naïve Bayes, Support Vector Machine, Logistic Regression, Stochastic Gradient Descent and Random Forest algorithms were used to compare performance. These classification algorithms were trained with the training data and tested with test dataset to determine the accuracy of the classifiers. Our model provides an average polarity of each features and an average polarity of the mobile phone which will give a rating of the device, thus assisting the customers to choose the best according to their desire. This project can work as an assistant for the customers to determine their device following the opinion of the other users of the device. ACKNOWLEDGEMENT Firstly, we would like to thank our Almighty for enabling us to conduct our research, give our best efforts and conclude it. Secondly, we would like to thank our supervisor Hossain Arif Sir for his feedback, support, guidance and contribution in conducting the research and preparation of the report. He encouraged us to conduct the research, guided us and always was present to offer any help we could ask for. We are grateful to him for his excellent supervision and effective guidance to successfully conduct our research. We extend our gratitude to our parents and friends, who helped us with kindness and inspiration and with their suggestions. We would also like to acknowledge our fellow researchers whose informative suggestions and numerous resources aided us to achieve our goal. Last but not the least, we thank BRAC University for providing us the opportunity of conducting this research and for giving us the chance to complete our Bachelor degree.

Detecting Online Recruitment Fraud Using Machine Learning

“…In Figure 4.1, the dataset without any pre-processing is shown. In this step, the inaccurate, irrelevant and incomplete data will be removed and will be cleaned to an extent where the machine learning algorithm will understand the overall content of the data [18]. This step is very crucial for any kind of data analysis as it can have an effect on the accuracy of the result.…”