Event Detection and User Interest Discovering in Social Media Data Streams - 2017

PROJECT TITLE :

Event Detection and User Interest Discovering in Social Media Data Streams - 2017

ABSTRACT:

Social media plays an increasingly necessary role in people’s life. Microblogging may be a form of social media that permits individuals to share and disseminate real-life events. Broadcasting events in microblogging networks can be an effective methodology of creating awareness, divulging important data, and therefore on. But, many existing approaches at dissecting the information content primarily discuss the event detection model and ignore the user interest that will be discovered throughout event evolution. This results in issue in tracking the foremost vital events as they evolve as well as identifying the influential spreaders. There is more complication given that the influential spreaders interests will also change during event evolution. The influential spreaders play a key role in event evolution and this has been largely ignored in ancient event detection methods. To this finish, we tend to propose a user-interest model-primarily based event evolution model, named the new event evolution model. This model not only considers the user interest distribution but conjointly uses the short text information within the social network to model the posts and the recommend ways to find the user interests. This can resolve the problem of knowledge sparsity, as exemplified by several existing event detection methods, and improve the accuracy of event detection. A hot event automatic filtering algorithm is initially applied to remove the influence of general events, improving the standard and efficiency of mining the event. Then, an automatic topic clustering algorithm is applied to arrange the short texts into clusters with similar topics. An improved user-interest model is proposed to mix the short texts of every cluster into a protracted text document simplifying the determination of the overall topic in relation to the interest distribution of every user throughout the evolution of vital events. Finally, a unique cosine live-primarily based event similarity detection technique is employed to assess correlation between events, thereby detecting the process of event evolution. The experimental results on a real Twitter information set demonstrate the potency and accuracy of our proposed model for each event detection and user interest discovery during the evolution of hot events.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here