Question and Accepted Answer Recommendation System with a Generic Knowledge Mining Visualization Tool

Abstract

With the increasing software developer community, questions answering (QA) sites, such as StackOverflow, Quora, Yahoo Answer etc. have been gaining its popularity. Hence, in recent years, millions of users are posting in StackOverflow. With the increase of users their question/answer a copious amount of data is generated, which attracts both the research community to utilize this information for extracting knowledge and the industry for developing the knowledge based systems.

Since it is really difficult to find a question that relates one’s expertise area in order to gain some extra reputation or bounty points, we have built a personalized recommender system named PRISM that will recommend posts to a user after login based on their expertise. We have also implemented our recommendation system web application which is currently deployed in our localhost.

Again it takes an enormous amount of effort to find out the suitable answer of a question. Propitiously, StackOverflow allows their community members to label an answer as an accepted answer. However, in the most of the questions answers are not marked as accepted answers. Therefore, there is a need to build a recommender system which can accurately suggest the most suitable answer to the questions. Contrary to the existing systems, in this work, we have utilized the textual features of the answers comments with the other metadata of the answers to build a recommender system for predicting the accepted answer called RAiTA. We have also deployed our recommendation system web application, which is publicly accessible at http://210.4.73.237:8888/

Visualization of data, pattern mining from datasets and analyzing data drift for the different features are three highly used applications of machine learning and data science fields. A generic web-based tool integrated with such features will provide prodigious support for pre-processing the dataset and thus extracting accurate information. In this work, we propose such a data visualization tool, named VIM which is publicly accessible at http://210.4.73.237:9999/