Analysis of Place Search using Natural Language Processing

The paper focuses on classifying the comments according to the sentiment which they express. Here, an effort has been made to extract comments on images and analyze the opinion of the people who use micro-blogging sites. The comment which reflect leaning of the users, can be categorized as positive, negative and neutral towards a particular place. For this purpose, the methodology we use is as follows: access the API to extract the comments about images. The extracted comments are then processed so as to convert all letters in the lower case, to special characters etc. which would make the further tasks more efficient. We classify these processed comments using a supervised classification approach. The classifier used is Naïve Bayes Classifier to classify the comments as positive, negative or neutral. The classifier is trained using comments which bear a distinctive polarity. The percentage of the positive and negative comment is then computed and is represented graphically. The result can be used further to gain an insight into the views of the people using micro-blogging site about a particular topic that is being searched by the user. It can help corporate houses to devise strategies on the basis of the popularity of their places among the masses.