ResearchPaperRecommendation - FindIt

FindIt is a software project designed to recommend research papers and articles based upon a given query.The system currently uses tfidf algorithm to extract the best score papers from the database.

Research Paper is defined as the ‘academic writing’ that contains the results and evaluation of original research conducted by researchers in various fields. It demonstrates the current activities ongoing in that area and is mostly referred to by all the researchers. However, the explosive growth of available digital information and the number of visitors to the Internet have created a potential challenge of information overload that hinders timely access to these items of interest on the Internet. It is necessary to enable the users to search through only those records of knowledge which are related to their interest and preference. This demand is meet using a ‘recommendation system’ that applies a decision making strategy to filter the relevant data from complex information environments. Recommender systems handle the problem of information overload that users normally encounter by providing them with personalized, exclusive content and service recommendations. It serves as a means of assisting and augmenting the social process of using recommendations of others to make choices when there is no sufficient personal knowledge or experience of the alternatives.

To enable users to search through relevant set of research papers, a ‘research paper recommendation system’ is used. This system filters relevant papers from the database of all sorts of papers using content based and collaborative filtering approaches of recommendation. Evaluation is done on the basis of correlation between the user’s profile section and the extracted features of research papers.Scoring is done on the basis of TFIDF strategy. We filter out items that a user might like on the basis of reactions by similar users. Thus the user-item relation from past references helps in recommending items in the current scenario.

This application software mainly targets Academia for its prospective users. Research papers are being widely read for gathering knowledge of ongoing work. The PhD scholars, the professional and the undergraduate researchers all over the world can be the common users of this system.They need to search for newly published papers on a regular basis.Considering the time constraint, they need a recommendation system that systematically ranks the papers of need.

Presentation and explaination of algorithms can be found here : https://docs.google.com/presentation/d/10Q--oYKR8cH8jL50ijDmG2zZjIHZfd0tBQmeFmWUmSc/edit?usp=sharing

Demo of the website is available at this youtube link : https://youtu.be/NxjUHSLsrIU

Share this project:

Updates