Finding Relevant Tweets

Deepak Padmanabhan, Sutanu Chakraborti

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

When a user of a microblogging site authors a microblog
post or browses through a microblog post, it provides cues as to what
topic she is interested in at that point in time. Example-based search
that retrieves similar tweets given one exemplary tweet, such as the one
just authored, can help provide the user with relevant content. We investigate
various components of microblog posts, such as the associated
timestamp, author’s social network, and the content of the post, and
develop approaches that harness such factors in finding relevant tweets
given a query tweet. An empirical analysis of such techniques on real
world twitter-data is then presented to quantify the utility of the various
factors in assessing tweet relevance. We observe that content-wise similar
tweets that also contain extra information not already present in the
query, are perceived as useful. We then develop a composite technique
that combines the various approaches by scoring tweets using a dynamic
query-specific linear combination of separate techniques. An empirical
evaluation establishes the effectiveness of the composite technique, and
that it outperforms each of its constituents.
LanguageEnglish
Title of host publicationWeb-Age Information Management - 13th International Conference, WAIM 2012, Harbin, China, August 18-20, 2012. Proceedings.
Pages228-240
Number of pages13
Publication statusPublished - 2012
EventWAIM 2012 - China, Harbin, China
Duration: 18 Aug 201220 Aug 2012

Conference

ConferenceWAIM 2012
CountryChina
CityHarbin
Period18/08/201220/08/2012

Fingerprint

Composite materials

Cite this

Padmanabhan, D., & Chakraborti, S. (2012). Finding Relevant Tweets. In Web-Age Information Management - 13th International Conference, WAIM 2012, Harbin, China, August 18-20, 2012. Proceedings. (pp. 228-240)
Padmanabhan, Deepak ; Chakraborti, Sutanu. / Finding Relevant Tweets. Web-Age Information Management - 13th International Conference, WAIM 2012, Harbin, China, August 18-20, 2012. Proceedings.. 2012. pp. 228-240
@inproceedings{5f9ba1f7019a477fb35def1a7116d6a5,
title = "Finding Relevant Tweets",
abstract = "When a user of a microblogging site authors a microblogpost or browses through a microblog post, it provides cues as to whattopic she is interested in at that point in time. Example-based searchthat retrieves similar tweets given one exemplary tweet, such as the onejust authored, can help provide the user with relevant content. We investigatevarious components of microblog posts, such as the associatedtimestamp, author’s social network, and the content of the post, anddevelop approaches that harness such factors in finding relevant tweetsgiven a query tweet. An empirical analysis of such techniques on realworld twitter-data is then presented to quantify the utility of the variousfactors in assessing tweet relevance. We observe that content-wise similartweets that also contain extra information not already present in thequery, are perceived as useful. We then develop a composite techniquethat combines the various approaches by scoring tweets using a dynamicquery-specific linear combination of separate techniques. An empiricalevaluation establishes the effectiveness of the composite technique, andthat it outperforms each of its constituents.",
author = "Deepak Padmanabhan and Sutanu Chakraborti",
year = "2012",
language = "English",
pages = "228--240",
booktitle = "Web-Age Information Management - 13th International Conference, WAIM 2012, Harbin, China, August 18-20, 2012. Proceedings.",

}

Padmanabhan, D & Chakraborti, S 2012, Finding Relevant Tweets. in Web-Age Information Management - 13th International Conference, WAIM 2012, Harbin, China, August 18-20, 2012. Proceedings.. pp. 228-240, WAIM 2012, Harbin, China, 18/08/2012.

Finding Relevant Tweets. / Padmanabhan, Deepak; Chakraborti, Sutanu.

Web-Age Information Management - 13th International Conference, WAIM 2012, Harbin, China, August 18-20, 2012. Proceedings.. 2012. p. 228-240.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Finding Relevant Tweets

AU - Padmanabhan, Deepak

AU - Chakraborti, Sutanu

PY - 2012

Y1 - 2012

N2 - When a user of a microblogging site authors a microblogpost or browses through a microblog post, it provides cues as to whattopic she is interested in at that point in time. Example-based searchthat retrieves similar tweets given one exemplary tweet, such as the onejust authored, can help provide the user with relevant content. We investigatevarious components of microblog posts, such as the associatedtimestamp, author’s social network, and the content of the post, anddevelop approaches that harness such factors in finding relevant tweetsgiven a query tweet. An empirical analysis of such techniques on realworld twitter-data is then presented to quantify the utility of the variousfactors in assessing tweet relevance. We observe that content-wise similartweets that also contain extra information not already present in thequery, are perceived as useful. We then develop a composite techniquethat combines the various approaches by scoring tweets using a dynamicquery-specific linear combination of separate techniques. An empiricalevaluation establishes the effectiveness of the composite technique, andthat it outperforms each of its constituents.

AB - When a user of a microblogging site authors a microblogpost or browses through a microblog post, it provides cues as to whattopic she is interested in at that point in time. Example-based searchthat retrieves similar tweets given one exemplary tweet, such as the onejust authored, can help provide the user with relevant content. We investigatevarious components of microblog posts, such as the associatedtimestamp, author’s social network, and the content of the post, anddevelop approaches that harness such factors in finding relevant tweetsgiven a query tweet. An empirical analysis of such techniques on realworld twitter-data is then presented to quantify the utility of the variousfactors in assessing tweet relevance. We observe that content-wise similartweets that also contain extra information not already present in thequery, are perceived as useful. We then develop a composite techniquethat combines the various approaches by scoring tweets using a dynamicquery-specific linear combination of separate techniques. An empiricalevaluation establishes the effectiveness of the composite technique, andthat it outperforms each of its constituents.

M3 - Conference contribution

SP - 228

EP - 240

BT - Web-Age Information Management - 13th International Conference, WAIM 2012, Harbin, China, August 18-20, 2012. Proceedings.

ER -

Padmanabhan D, Chakraborti S. Finding Relevant Tweets. In Web-Age Information Management - 13th International Conference, WAIM 2012, Harbin, China, August 18-20, 2012. Proceedings.. 2012. p. 228-240