Opinion Mining using Machine Learning

Abstract: Information contained in opinion can be either subjective or objective or both. Subjective form contains positive or negative opinions, while objective form contains the facts. Identifying the subjectivity and objectivity of information is the outcome of Opinion Mining and Sentiment Analysis. The result will be either positive or negative or a mix of both. Machine learning enables the computers to act without being explicitly programmed for a particular task. Applications of the machine learning include self-driving cars, effective web search, practical speech recognition etc.We use machine learning several times a day without knowing it. The developments in this area have resulted in human-level artificial intelligence. Todesign innovative marketing strategies, opinion mining and sentiment analysis are being used in recent days. Using generated analog data, subjective content is extracted and prediction of subjectivity such as positive or negative is done. This information helps to build systems to understand customer’s feedback and plan business strategies accordingly. This also helps in predicting the chances of product failure.In this paper, it is explained how machine learning can be used for opinion mining.

Keywords:Machine Learning,Opinion Mining, Sentiment Analysis, Classification

INTRODUCTION

Machine learning framework is an integrated system of programs. These programs learn from existing data and capable of predicting new observations. Machine learning deals with the systems study that learns from data, instead of following explicitly programmed instructions. This technique is used in a wide range of computing tasks. Opinion originates from state of mind, when we experience something in our day to day life. The expression may be an appraisal or a negative comment. Some of the typical techniques to identify and predict the sentiments from the text are Lexicon, Natural Language Processing, Machine Learning based techniques. In this study, we have used Machine learning based technique to extract opinions of customers and use it for business. The approach is quite straightforward; record customer‟s opinion, train and classify on selected key words. Similarly, opinion can be predicted by using a pre-populated list of positive and negative words. For example,in the sentence “performance of XYZ Laptop is not good”, the word „good‟ is a positive word but presence of word „not‟ contradicts polar nature of the word. Simple negative and positive word combination creates a negative expression.
Read More