Rank Based Hindi News Recommendation System Using LSTM ANN Approach
Abstract
With the enormous evolution of communication systems along with the electronic gadget, access to information has become easier. This affects daily life, as users demand information at a rate that is not required on a daily basis and present new challenges for content owners. In the field of news, this scenario is faced the most, given the large number of daily news articles and ephemeral time. New reading has also been affected by the more powerful mobile gadget. Rank based recommendation systems are often used to help content providers to filter out critical information and meaningful information’s based on the entered keywords by providing the data with the most relevant news portal. In this paper, a rank- based recommendation system has been presented by using the concept of Artificial Intelligence. The system has been designed by applying pre-processing (stop-word removal with word to vector) approach, feature extraction model (TF-IDF) scheme and then trained the model. The validation of model has been done by passing query words; output has been obtained in the form of most appropriate news portal, having maximum similarity score. The performance has been measured in terms of precision, recall, F-score and accuracy.