%0 Conference Paper %1 Duan:2010:ESL:1873781.1873815 %A Duan, Yajuan %A Jiang, Long %A Qin, Tao %A Zhou, Ming %A Shum, Heung-Yeung %B Proceedings of the 23rd International Conference on Computational Linguistics %C Stroudsburg, PA, USA %D 2010 %I Association for Computational Linguistics %K learning rank thema thema:learning-to-rank to tweet twitter %P 295--303 %T An empirical study on learning to rank of tweets %U http://dl.acm.org/citation.cfm?id=1873781.1873815 %X Twitter, as one of the most popular micro-blogging services, provides large quantities of fresh information including real-time news, comments, conversation, pointless babble and advertisements. Twitter presents tweets in chronological order. Recently, Twitter introduced a new ranking strategy that considers popularity of tweets in terms of number of retweets. This ranking method, however, has not taken into account content relevance or the twitter account. Therefore a large amount of pointless tweets inevitably flood the relevant tweets. This paper proposes a new ranking strategy which uses not only the content relevance of a tweet, but also the account authority and tweet-specific features such as whether a URL link is included in the tweet. We employ learning to rank algorithms to determine the best set of features with a series of experiments. It is demonstrated that whether a tweet contains URL or not, length of tweet and account authority are the best conjunction.

@inproceedings{Duan:2010:ESL:1873781.1873815, abstract = {Twitter, as one of the most popular micro-blogging services, provides large quantities of fresh information including real-time news, comments, conversation, pointless babble and advertisements. Twitter presents tweets in chronological order. Recently, Twitter introduced a new ranking strategy that considers popularity of tweets in terms of number of retweets. This ranking method, however, has not taken into account content relevance or the twitter account. Therefore a large amount of pointless tweets inevitably flood the relevant tweets. This paper proposes a new ranking strategy which uses not only the content relevance of a tweet, but also the account authority and tweet-specific features such as whether a URL link is included in the tweet. We employ learning to rank algorithms to determine the best set of features with a series of experiments. It is demonstrated that whether a tweet contains URL or not, length of tweet and account authority are the best conjunction.}, acmid = {1873815}, added-at = {2016-09-23T11:36:38.000+0200}, address = {Stroudsburg, PA, USA}, author = {Duan, Yajuan and Jiang, Long and Qin, Tao and Zhou, Ming and Shum, Heung-Yeung}, biburl = {https://www.bibsonomy.org/bibtex/2cf6a7ced9092f46b77b5cd3c979c47d0/nosebrain}, booktitle = {Proceedings of the 23rd International Conference on Computational Linguistics}, interhash = {2f032e61db8d2a0ae39314ccd228e41f}, intrahash = {cf6a7ced9092f46b77b5cd3c979c47d0}, keywords = {learning rank thema thema:learning-to-rank to tweet twitter}, location = {Beijing, China}, numpages = {9}, pages = {295--303}, publisher = {Association for Computational Linguistics}, series = {COLING '10}, timestamp = {2016-10-05T18:45:59.000+0200}, title = {An empirical study on learning to rank of tweets}, url = {http://dl.acm.org/citation.cfm?id=1873781.1873815}, year = 2010 }