Result Diversification for Tweet Search

Abstract

Abstract. Being one of the most popular microblogging platforms, Twitter handles more than two billion queries per day. Given the users' desire for fresh and novel content but their reluctance to submit long and descriptive queries, there is an inevitable need for generating diversified search results to cover different aspects of a query topic. In this paper, we address diversification of results in tweet search by adopting several methods from the text summarization and web search domains. We provide an exhaustive evaluation of all the methods using a standard dataset specifically tailored for this purpose. Our findings reveal that implicit diversification methods are more promising in the current setup, whereas explicit methods need to be augmented with a better representation of query sub-topics.

Region-Based Message Exploration over Spatio-Temporal Data Streams

“…First of all, most of the users prefer receiving summary information that satisfies their interested topics and location-based patterns rather than receiving a list of raw items (Farzindar and Khreich 2015;Tobler 1970). Secondly, users may receive a set of nearduplicate messages (Ozsoy, Onal, and Altingovde 2014), which greatly reduce the result diversity and topic coverage. Thirdly, it is difficult for users to understand the key topics and the local distribution of a large number of result spatio-temporal messages within a few seconds.…”

Spatio-temporal top-k term search over sliding window

“…Data streams from location-based social media bear the following natures: (1) bursty nature -messages regarding a particular topic can be quickly buried deep in the stream if the user is not fast enough to discover it [28]; (2) localintended nature -users from different locations may post messages related to diverging topics [62]. With thousands of messages being generated from location-based social media each second, it is of great importance to maintain a summary of what occupies minds of users.…”