I am trying to build a Recommendation system on my website for recommending similar articles to the user. Eg: Lets say a user is reading an article about sports on a news website. The next article should be related to sports. I have a dataset with a set of links to different articles.
Currently, I have the Page_title, Tags, Article content. I ran some NER's on the article content and found out important keywords. Then I have used Jaccard Similarity for combining the matrix from all 3 features and finding similarity between these links.
Is something wrong with my method? Can it be improved? How do websites solve this problem?
I am constrained by the data that I have.