Urdu News Article Recommendation Model using Natural Language Processing Techniques
This addresses a domain-specific problem for Urdu news readers by providing an incremental improvement in recommendation accuracy.
The paper tackles the problem of users struggling to find relevant Urdu news articles by proposing a recommendation model that uses NLP techniques, including TF-IDF and BERT, to predict user interests and reduce search time, achieving a similarity threshold of 60% for recommendations.
There are several online newspapers in urdu but for the users it is difficult to find the content they are looking for because these most of them contain irrelevant data and most users did not get what they want to retrieve. Our proposed framework will help to predict Urdu news in the interests of users and reduce the users searching time for news. For this purpose, NLP techniques are used for pre-processing, and then TF-IDF with cosine similarity is used for gaining the highest similarity and recommended news on user preferences. Moreover, the BERT language model is also used for similarity, and by using the BERT model similarity increases as compared to TF-IDF so the approach works better with the BERT language model and recommends news to the user on their interest. The news is recommended when the similarity of the articles is above 60 percent.