Celebrity Profiling

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2611–2618 Florence, Italy, July 28 - August 2, 2019. c⃝2019 Association for Computational Linguistics 2611 Celebrity Profiling Matti Wiegmann1,2 Benno Stein1 Martin Potthast3 1Bauhaus-Universität Weimar 2German Aerospace Center 3Leipzig University <first>.<last>@[uni-weimar|dlr|uni-leipzig].de 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 con- struction the Twitter feeds of 71,706 verified accounts have been carefully linked with their respective Wikidata items, crawling both. Af- ter 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 pro- files highly reliable. Our corpus comprises a wide cross-section of local and global celebri- ties, forming a unique combination of scale, profile comprehensiveness, and label reliabil- ity. We further establish the state of the art’s profiling performance by evaluating the win- ning approaches submitted to the PAN gender prediction tasks in a transfer learning experi- ment. They are only outperformed by our own deep learning approach, which we also use to exemplify celebrity occupation prediction for the first time. 1 Introduction Author profiling is about predicting personal traits of individual authors based on their writing style. Frequently studied traits are demographics such as gender, age, native language or dialect, and even personality. Applications of author profiling in- clude marketing, social science, risk assessment, and forensics. Given the high expectations that are implied by these and similar applications, the cre- ation of a valid automatic profiler for a given trait, let alone many, depends on the availability of care- fully constructed corpora. Corpus construction for author profiling has always been difficult for lack of large-scale distant supervision sources that provide for genuine pieces of writing from many different authors alongside personal information. In part, the aforementioned selection of demographics that are frequently studied reflects the availability of corre- sponding ground truth. In this regard, one source of ground truth, available in large quantities, high diversity of traits, and near-perfect label reliability, has been overlooked: celebrities. The contributions of our research are threefold:1 First, in Section 2, we survey the state of the art in constructing author profiling corpora for the first time, compiling a taxonomy of construction strate- gies applied. Second, in Section 3, we report on the construction of the first large-scale corpus of celebrity profiles, describing our acquisition ap- proach based on a reliable matching of Twitter accounts to Wikidata items. Third, in Section 4, we carry out a prediction experiment on the most widely studied trait, gender, comparing the perfor- mance of our own deep learning approach with that of the four best-performing ones submitted to the recent …

Content truncated to 500 words