In microblogging services such as Twitter, the users may become overwhelmed by the raw data. One solution to this problem is the classification of short text messages. As short texts do not provide sufficient word occurrences, traditional classification methods such as "Bag-Of-Words" have limitations. To address this problem, we propose to use a small set of domain-specific features extracted from the author's profile and text. The proposed approach effectively classifies the text to a predefined set of generic classes such as News, Events, Opinions, Deals, and Private Messages.
Description
Short text classification in twitter to improve information filtering
%0 Conference Paper
%1 Sriram:2010:STC:1835449.1835643
%A Sriram, Bharath
%A Fuhry, Dave
%A Demir, Engin
%A Ferhatosmanoglu, Hakan
%A Demirbas, Murat
%B Proceedings of the 33rd International ACM SIGIR Conference on Research and Development in Information Retrieval
%C New York, NY, USA
%D 2010
%I ACM
%K classification expert_finding twitter
%P 841--842
%R 10.1145/1835449.1835643
%T Short Text Classification in Twitter to Improve Information Filtering
%U http://doi.acm.org/10.1145/1835449.1835643
%X In microblogging services such as Twitter, the users may become overwhelmed by the raw data. One solution to this problem is the classification of short text messages. As short texts do not provide sufficient word occurrences, traditional classification methods such as "Bag-Of-Words" have limitations. To address this problem, we propose to use a small set of domain-specific features extracted from the author's profile and text. The proposed approach effectively classifies the text to a predefined set of generic classes such as News, Events, Opinions, Deals, and Private Messages.
%@ 978-1-4503-0153-4
@inproceedings{Sriram:2010:STC:1835449.1835643,
abstract = {In microblogging services such as Twitter, the users may become overwhelmed by the raw data. One solution to this problem is the classification of short text messages. As short texts do not provide sufficient word occurrences, traditional classification methods such as "Bag-Of-Words" have limitations. To address this problem, we propose to use a small set of domain-specific features extracted from the author's profile and text. The proposed approach effectively classifies the text to a predefined set of generic classes such as News, Events, Opinions, Deals, and Private Messages.},
acmid = {1835643},
added-at = {2014-12-15T16:35:28.000+0100},
address = {New York, NY, USA},
author = {Sriram, Bharath and Fuhry, Dave and Demir, Engin and Ferhatosmanoglu, Hakan and Demirbas, Murat},
biburl = {https://www.bibsonomy.org/bibtex/2c53415eb32cf67a68f234322b9c8715f/asmelash},
booktitle = {Proceedings of the 33rd International ACM SIGIR Conference on Research and Development in Information Retrieval},
description = {Short text classification in twitter to improve information filtering},
doi = {10.1145/1835449.1835643},
interhash = {6791506b492d4682a60addcf17477ec1},
intrahash = {c53415eb32cf67a68f234322b9c8715f},
isbn = {978-1-4503-0153-4},
keywords = {classification expert_finding twitter},
location = {Geneva, Switzerland},
numpages = {2},
pages = {841--842},
publisher = {ACM},
series = {SIGIR '10},
timestamp = {2014-12-15T16:35:28.000+0100},
title = {Short Text Classification in Twitter to Improve Information Filtering},
url = {http://doi.acm.org/10.1145/1835449.1835643},
year = 2010
}