SHEDR: An End-to-End Neural Event Detection and Recommendation Framework for Hyperlocal News Using Social Media

Residents often rely on newspapers and television to gather hyperlocal news for community awareness and engagement. More recently, social media have emerged as an increasingly important source of hyperlocal news. Thus far, the Information System (IS) literature on using social media to create desirable societal benefits, such as civic awareness and engagement, is still in its infancy. One key challenge in this research stream is to timely and accurately distill information from noisy social media data streams to community members. In this work, we develop SHEDR (Social Me-dia-based Hyperlocal Event Detection & Recommendation), an end-to-end neural event detection and recommendation framework on Twitter to facilitate residents’ information-seeking of hyperlo-cal events. The key innovation in SHDER lies in the design of the hyperlocal event detector and the event recommender. First, we harness the power of two popular deep neural network models, CNN and LSTM, in a joint CNN-LSTM model to characterize spatial-temporal dependencies for capturing unusualness in a region of interest, which is classified as a hyperlocal event. Next, we develop a neural pair-wise ranking algorithm for recommending detected hyperlocal events t resi-dents based on their interests. To alleviate the sparsity issue and improve personalization, our algo-rithm incorporates several types of contextual information covering topic, social and geographical proximities. We perform comprehensive evaluations based on two large scale datasets comprising geotagged tweets covering Seattle and Chicago. We demonstrate the effectiveness of our frame-work in comparison to several state-of-the-art approaches. We show that our hyperlocal event de-tection and recommendation models consistently and significantly outperform other approaches in terms of precision, recall, and F-1 scores.