Personalized News Recommendation based on Multi-agent framework using Social Media Preferences

摘要

Staying updated about global events is a necessity for the modern day man. Many sources for latest news are available on the web, and individuals can make use of their favorite news source to get the daily news, but most of the time they are unable to get the news of desired interest. There is a need to analyze the news and rank them according to user's interest. Social media can provide an insight on a user's likes and dislikes, which used for news recommendation. This paper presents a multi-agent framework [1] that uses a novel methodology for ranking news articles on the basis of user's interests fetched from social media [2]. To do so, we have modeled the relationship between user's social media preferences and news categories: we have extracted categories from social media, mapped with general news categories. Our developed solution provides 28% better results than current news websites recommendation. Further experimentations show that our solution provides effective news recommendation as it makes use of the user's social media profile [3], which always updated and maintained by the user firsthand. Another important objective is to increase positivity in one's life. These days the world is in turmoil due to terrorism activities [4].These activities naturally attract media coverage, presenting an unpleasant view of various regions of the world. Although there are many good things/activities happening around us, we mostly see violence and hate speech everywhere on the web [5]. Sentiment analysis is a technique used to extract the impact of the statement i.e. weather the statement is positive or negative [6], [7], and [8]. Sentiment analysis used to filter news based on harmful negative activities and displaying positive news of latest inventions in world, advancement in the industry, relief packages from governments and other growth opportunities. Based on these ideas, we have developed an android application and performed a pilot study. Our results show higher satisfaction levels for users when searching news articles through the proposed system.