Quora: Finding The Most Common Question Pairs Similarity

Abstract

Data mining is the ability to extract the most relevant information from raw data and process the relevant information into a separate list. In general, the word ontology is termed an alternate name for data mining, in which extracting useful information from the big data sources is the most common task present in the ontology domain. In current days the semantic web is becoming a more trending topic for a lot of new research inventions. One of the recent research inventions is finding the most common question pair similarity from several questions and answers which are published on certain topics on the semantic web. This is becoming a challenge for the developers to prove this task and hence this is the main motivation for me to design this current work in which one will get a lot of useful information from this research topic. For testing this current model we assume QUORA as the sample data source in which a group of several question-and-answers is asked, answered, edited, and organized by its community of users. On this site lot of end, users can collaborate with each other for certain questions, share their suggestions, and edit the answers which are already submitted by others. This collaboration is taken as a thread on a single question with a list of similar/related questions so that users would not have to answer similar questions once again. By using the several various Natural Language Processing (NLP) concepts from the given dataset and applying several ML algorithms on that input features, we try to fund our most distinct question and answers and remove the duplicates which are present for a certain topic.