%0 Conference Paper %1 wiegmann-etal-2019-celebrity %A Wiegmann, Matti %A Stein, Benno %A Potthast, Martin %B Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics %C Florence, Italy %D 2019 %E Korhonen, Anna %E Traum, David %E Màrquez, Llu\'ıs %I Association for Computational Linguistics %K imported %P 2611--2618 %R 10.18653/v1/P19-1249 %T Celebrity Profiling %U https://aclanthology.org/P19-1249 %X Celebrities are among the most prolific users of social media, promoting their personas and rallying followers. This activity is closely tied to genuine writing samples, which makes them worthy research subjects in many respects, not least profiling. With this paper we introduce the Webis Celebrity Corpus 2019. For its construction the Twitter feeds of 71,706 verified accounts have been carefully linked with their respective Wikidata items, crawling both. After cleansing, the resulting profiles contain an average of 29,968 words per profile and up to 239 pieces of personal information. A cross-evaluation that checked the correct association of Twitter account and Wikidata item revealed an error rate of only 0.6\%, rendering the profiles highly reliable. Our corpus comprises a wide cross-section of local and global celebrities, forming a unique combination of scale, profile comprehensiveness, and label reliability. We further establish the state of the art's profiling performance by evaluating the winning approaches submitted to the PAN gender prediction tasks in a transfer learning experiment. They are only outperformed by our own deep learning approach, which we also use to exemplify celebrity occupation prediction for the first time.

@inproceedings{wiegmann-etal-2019-celebrity, abstract = {Celebrities are among the most prolific users of social media, promoting their personas and rallying followers. This activity is closely tied to genuine writing samples, which makes them worthy research subjects in many respects, not least profiling. With this paper we introduce the Webis Celebrity Corpus 2019. For its construction the Twitter feeds of 71,706 verified accounts have been carefully linked with their respective Wikidata items, crawling both. After cleansing, the resulting profiles contain an average of 29,968 words per profile and up to 239 pieces of personal information. A cross-evaluation that checked the correct association of Twitter account and Wikidata item revealed an error rate of only 0.6{\%}, rendering the profiles highly reliable. Our corpus comprises a wide cross-section of local and global celebrities, forming a unique combination of scale, profile comprehensiveness, and label reliability. We further establish the state of the art{'}s profiling performance by evaluating the winning approaches submitted to the PAN gender prediction tasks in a transfer learning experiment. They are only outperformed by our own deep learning approach, which we also use to exemplify celebrity occupation prediction for the first time.}, added-at = {2024-10-02T10:38:17.000+0200}, address = {Florence, Italy}, author = {Wiegmann, Matti and Stein, Benno and Potthast, Martin}, biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/20658c2dbf9b3ee5672c472f2c2de1e0c/scadsfct}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1249}, editor = {Korhonen, Anna and Traum, David and M{\`a}rquez, Llu{\'\i}s}, interhash = {0a3f9c09a131573a4b8680e2599e2a5c}, intrahash = {0658c2dbf9b3ee5672c472f2c2de1e0c}, keywords = {imported}, month = jul, pages = {2611--2618}, publisher = {Association for Computational Linguistics}, timestamp = {2024-10-02T10:38:17.000+0200}, title = {Celebrity Profiling}, url = {https://aclanthology.org/P19-1249}, year = 2019 }