TweetGenie is an online demo that infers the gender and age of Twitter users based on their tweets. TweetGenie was able to attract thousands of visitors. We collected data by asking feedback from visitors and launching an online game. In this paper, we describe the development of TweetGenie and evaluate the demo based on the received feedback and manual annotation. We also reflect on practical lessons learned from launching a demo for the general public.
|Title of host publication||Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: System Demonstrations|
|Place of Publication||Dublin|
|Publisher||Association for Computational Linguistics (ACL)|
|Number of pages||5|
|Publication status||Published - 2014|
Nguyen, D., Trieschnigg, D., & Meder, T. (2014). Tweetgenie: Development, Evaluation, and Lessons Learned. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: System Demonstrations (pp. 62-66). Association for Computational Linguistics (ACL). http://anthology.aclweb.org/C/C14/C14-2014.pdf