Effectiveness of state-of-the-art features for microblog search

Abstract

We investigate in this paper information retrieval in microblogs exploiting different state-of-the-art features. Microbloggers, besides posting microblogs, search for fresh and relevant information related to their interests, by submitting a query to a microblog search engine. The majority of approaches that collect information from microblogs exploit features such as the recency of the microblog, the authority of his/her author. . . to improve the quality of their results. In this paper, we evaluated some of the state-of-theart features to determine those that discriminate relevant from irrelevant microblogs given an information need. Then, we used the selected features to learn models to determine their effectiveness in a microblog search task. We conducted a series of experiments using the dataset and topics of the TREC Microblog 2011 and 2012 tracks. Results show that content, hypertextuality, and recency are the best predictors of relevance. We also found that Naive Bayes was the most effective learning approach for this type of classification.

A probabilistic model to exploit user expectations in XML information retrieval

“…Huurdeman, Kamps, Koolen, and Wees (2012) have exploited the number of reviews, the rating average and the user tag frequencies in the social information retrieval. Damak, Pinel-Sauvagnat, Boughanem, and Cabanac (2013) have introduced the language quality and Badache, & Boughanem, (2015) have exploited social signals such as the number of user likes and shares.…”

A Distributed Multi-facet Search Engine of Microblogs Based on SolrCloud

“…These different features present challenges as well as new opportunities to microblog search engines. Several previous studies have tried combining some of these features to form a better ranking algorithm for microblogs [8,10,11], usually with the help of machine learning. For example, Damak et al's study [8] found that tweet popularity, length, exact term matching, URL presence, URL popularity in the corpus, URL frequency in the microblog and the recency of the microblog were the best relevance indicators.…”

“…However, the distinct features of microblogs as well as the sheer amount of them bring significant challenges to tools that aim to efficiently and effectively mine useful information from these messages. Microblog messages differ from conventional Web pages in various aspects [8]. Furthermore, people look for different things in microblogs and search in different ways [9].…”

Towards Events Tweet Contextualization Using Social Influence Model and Users Conversations

“…• Similarity of content [8] In our case, it measures how many tweet of the whole conversation C are similar in content with current tweet t current . We calculate cosine similarity score for every pair of tweets.…”