"How Old Do You Think I Am?" A Study of Language and Age in Twitter

Dong Nguyen; Rilana Gravel; Dolf Trieschnigg; Theo Meder

"How Old Do You Think I Am?" A Study of Language and Age in Twitter

Dong Nguyen, Rilana Gravel, Dolf Trieschnigg, Theo Meder

School of Informatics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Multilingual speakers switch between languages in online and spoken communication. Analyses of large scale multilingual data require automatic language identification at the word level. For our experiments with multilingual online discussions, we first tag the language of individual words using language models and dictionaries. Secondly, we incorporate context to improve the performance. We achieve an accuracy of 98%. Besides word level accuracy, we use two new metrics to evaluate this task.

Original language	English
Title of host publication	Proceedings of the Seventh International Conference on Weblogs and Social Media, ICWSM 2013, Cambridge, Massachusetts, USA, July 8-11, 2013.
Publisher	The AAAI Press
Pages	857–862
Number of pages	6
Publication status	Published - 28 Jun 2013

Access to Document

5984-30392-1-PBFinal published version, 526 KB

http://www.aaai.org/ocs/index.php/ICWSM/ICWSM13/paper/view/5984

Cite this

Nguyen, D., Gravel, R., Trieschnigg, D., & Meder, T. (2013). "How Old Do You Think I Am?" A Study of Language and Age in Twitter. In Proceedings of the Seventh International Conference on Weblogs and Social Media, ICWSM 2013, Cambridge, Massachusetts, USA, July 8-11, 2013. (pp. 857–862). The AAAI Press. http://www.aaai.org/ocs/index.php/ICWSM/ICWSM13/paper/view/5984

@inproceedings{c7ecf1256fd0483ba00cd2c2fbb452ce,

title = "{"}How Old Do You Think I Am?{"} A Study of Language and Age in Twitter",

abstract = "Multilingual speakers switch between languages in online and spoken communication. Analyses of large scale multilingual data require automatic language identification at the word level. For our experiments with multilingual online discussions, we first tag the language of individual words using language models and dictionaries. Secondly, we incorporate context to improve the performance. We achieve an accuracy of 98%. Besides word level accuracy, we use two new metrics to evaluate this task.",

author = "Dong Nguyen and Rilana Gravel and Dolf Trieschnigg and Theo Meder",

year = "2013",

month = jun,

day = "28",

language = "English",

pages = "857–862",

booktitle = "Proceedings of the Seventh International Conference on Weblogs and Social Media, ICWSM 2013, Cambridge, Massachusetts, USA, July 8-11, 2013.",

publisher = "The AAAI Press",

}

"How Old Do You Think I Am?" A Study of Language and Age in Twitter. / Nguyen, Dong; Gravel, Rilana; Trieschnigg, Dolf; Meder, Theo.

Proceedings of the Seventh International Conference on Weblogs and Social Media, ICWSM 2013, Cambridge, Massachusetts, USA, July 8-11, 2013.. The AAAI Press, 2013. p. 857–862.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - "How Old Do You Think I Am?" A Study of Language and Age in Twitter

AU - Nguyen, Dong

AU - Gravel, Rilana

AU - Trieschnigg, Dolf

AU - Meder, Theo

PY - 2013/6/28

Y1 - 2013/6/28

N2 - Multilingual speakers switch between languages in online and spoken communication. Analyses of large scale multilingual data require automatic language identification at the word level. For our experiments with multilingual online discussions, we first tag the language of individual words using language models and dictionaries. Secondly, we incorporate context to improve the performance. We achieve an accuracy of 98%. Besides word level accuracy, we use two new metrics to evaluate this task.

AB - Multilingual speakers switch between languages in online and spoken communication. Analyses of large scale multilingual data require automatic language identification at the word level. For our experiments with multilingual online discussions, we first tag the language of individual words using language models and dictionaries. Secondly, we incorporate context to improve the performance. We achieve an accuracy of 98%. Besides word level accuracy, we use two new metrics to evaluate this task.

M3 - Conference contribution

SP - 857

EP - 862

BT - Proceedings of the Seventh International Conference on Weblogs and Social Media, ICWSM 2013, Cambridge, Massachusetts, USA, July 8-11, 2013.

PB - The AAAI Press

ER -

"How Old Do You Think I Am?" A Study of Language and Age in Twitter

Abstract

Access to Document

Fingerprint

Cite this