PROJECT TITLE :
Hashtagger+: Efficient High-Coverage Social Tagging of Streaming News - 2018
News and social media currently play a synergistic role and neither domain can be grasped in isolation. On one hand, platforms such as Twitter have taken a central role within the dissemination and consumption of reports. On the opposite hand, news editors depend upon social media for following their audience's attention and for crowd-sourcing news stories. Twitter hashtags function as a key connection between Twitter crowds and the news media, by naturally naming and contextualizing stories, grouping the discussion of stories and marking topic trends. In this work, we have a tendency to propose Hashtagger+, an efficient learning-to-rank framework for merging news and social streams in real-time, by recommending Twitter hashtags to news articles. We tend to offer an extensive study of various approaches for streaming hashtag recommendation, and show that pointwise learning-to-rank is a lot of effective than multi-class classification along with additional complicated learning-to-rank approaches. We tend to improve the potency and coverage of a state-of-the-art hashtag recommendation model by proposing new techniques for information collection and have computation. In our comprehensive analysis on real-data, we tend to show that we tend to drastically outperform the accuracy and efficiency of prior strategies. Our prototype system delivers recommendations in under one minute, with a Precision@one of ninety four percent and article coverage of eighty %. This can be an order of magnitude faster than prior approaches, and brings improvements of five % in precision and 20 percent in coverage. By effectively linking the news stream to the social stream via the counseled hashtags, we tend to open the door to solving several difficult issues related to story detection and tracking. To showcase this potential, we present an application of our recommendations to automated news story tracking via social tags. Our recommendation framework is implemented in a very real-time Web system obtainable from insight4news.ucd.ie.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here