A longitudinal study of topic classification on Twitter Iman, Z, Sanner, S, Bouadjenek, Mohamed Reda and Xie, L 2017, A longitudinal study of topic classification on Twitter, in Proceedings of the 11th International Conference on Web and Social Media, ICWSM 2017, AAAI,, pp. 552-555. Attached Files Name Description MIMEType Size Downloads Title A longitudinal study of topic classification on Twitter Author(s) Iman, Z Sanner, S Bouadjenek, Mohamed Reda orcid.org/0000-0003-1807-430X Xie, L Conference name Eleventh International AAAI Conference on Web and Social Media Conference location Montreal, Canada Conference dates 2017/05/15 - 2017/05/18 Title of proceedings Proceedings of the 11th International Conference on Web and Social Media, ICWSM 2017 Publication date 2017 Start page 552 End page 555 Total pages 4 Publisher AAAI Summary © Copyright 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. Twitter represents a massively distributed information source over a kaleidoscope of topics ranging from social and political events to entertainment and sports news. While recent work has suggested that variations on standard classifiers can be effectively trained as topical filters (Lin, Snow, and Morgan 2011; Yang et al. 2014; Magdy and Elsayed 2014), there remain many open questions about the efficacy of such classification-based filtering approaches. For example, over a year or more after training, how well do such classifiers generalize to future novel topical content, and are such results stable across a range of topics? Furthermore, what features and feature classes are most critical for longterm classifier performance? To answer these questions, we collected a corpus of over 800 million English Tweets via the Twitter streaming API during 2013 and 2014 and learned topic classifiers for 10 diverse themes ranging from social issues to celebrity deaths to the "Iran nuclear deal". The results of this long-term study of topic classifier performance provide a number of important insights, among them that (1) such classifiers can indeed generalize to novel topical content with high precision over a year or more after training and (2) simple terms and locations are the most informative feature classes (despite training on classes labeled via hashtags). ISBN 9781577357889 Indigenous content off HERDC Research category E3.1 Extract of paper Persistent URL http://hdl.handle.net/10536/DRO/DU:30131229 Document type: Conference Paper Collections: Faculty of Science, Engineering and Built Environment School of Information Technology Related Links Link Description Connect to Elements publication management system Go to link with your DU access privileges     Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved. Versions Version Filter Type Sat, 02 Nov 2019, 10:21:04 EST Sun, 03 Nov 2019, 04:00:22 EST Mon, 04 Nov 2019, 06:59:54 EST Thu, 07 Nov 2019, 05:03:02 EST Sun, 07 Nov 2021, 12:41:22 EST Sun, 07 Nov 2021, 13:27:05 EST Sun, 07 Nov 2021, 13:33:52 EST Filtered Full Citation counts:   Cited 0 times in TR Web of Science Cited 6 times in Scopus Search Google Scholar Access Statistics: 9 Abstract Views, 0 File Downloads  -  Detailed Statistics Created: Sat, 02 Nov 2019, 10:21:04 EST