Author Profiling
2016

Adobe
Sponsor
MeaningCloud
Sponsor

Authorship analysis deals with the classification of texts into classes based on the stylistic choices of their authors. Beyond the author identification and author verification tasks where the style of individual authors is examined, author profiling distinguishes between classes of authors studying their sociolect aspect, that is, how language is shared by people. This helps in identifying profiling aspects such as gender, age, native language, or personality type. Author profiling is a problem of growing importance in applications in forensics, security, and marketing. E.g., from a forensic linguistics perspective one would like being able to know the linguistic profile of the author of a harassing text message (language used by a certain type of people) and identify certain characteristics (language as evidence). Similarly, from a marketing viewpoint, companies may be interested in knowing, on the basis of the analysis of blogs and online product reviews, the demographics of people that like or dislike their products. The focus is on author profiling in social media since we are mainly interested in everyday language and how it reflects basic social and personality processes.

Award

We are happy to announce that the best performing team at the 4th International Competition on Author Profiling will be awarded 300,- Euro sponsored by MeaningCloud.

  • Mart Busger op Vollenbroek, Talvany Carlotto, Tim Kreutz, Maria Medvedeva, Chris Pool, Johannes Bjerva, Hessel Haagsma, Malvina Nissim. University of Groningen, Netherlands.

Congratulations!

Task

The focus of 2016 shared task is on cross-genre age and gender identification. That is, the training documents will be on one genre (e.g. Twitter, blogs, social media...) and the evaluation will be on another genre (e.g. Twitter, blogs, social media...).

Three languages will be addressed: English, Spanish and Dutch.

Training corpus

To develop your software, we provide you with a training data set that consists of Twitter tweets in English, Spanish and Dutch.

Download corpus (Updated April 25, 2016)

The English and Spanish datasets are labeled with age and gender, whereas the Dutch one only with gender. With regard to age, we will consider the following classes: 18-24, 25-34, 35-49, 50-64, 65-xx.

Remark. Due to Twitter's privacy policy we cannot provide tweets directly, but only URLs referring to them. You will have to download them yourself. For your convenience, we provide a download software for this. We expect participants to extract gender and age information only from the textual part of a tweet and to discard any other meta information that may be provided by Twitter's API. When we evaluate your software at our site, we do not expect it downloads tweets. We will do this beforehand.

Download software

Output

Your software must take as input the absolute path to an unpacked dataset, and has to output for each document of the dataset a corresponding XML file that looks like this:

  <author id="{author-id}"
	  type="not relevant"
	  lang="en|es|nl"
	  age_group="18-24|25-34|35-49|50-64|65-xx"
	  gender="male|female"
  />
  

The naming of the output files is up to you, we recommend to use the author-id as filename and "xml" as extension.

Performance Measures

The performance of your author profiling solution will be ranked by accuracy.

Concretely, we will calculate individual accuracies for each language, gender, and age class. Then, we will average the accuracy values to obtain a joint identification of age and gender in each language.

Submission

We ask you to prepare your software so that it can be executed via command line calls. More details will be released here soon.

You can choose freely among the available programming languages and among the operating systems Microsoft Windows and Ubuntu. We will ask you to deploy your software onto a virtual machine that will be made accessible to you after registration. You will be able to reach the virtual machine via ssh and via remote desktop. More information about how to access the virtual machines can be found in the user guide below:

PAN Virtual Machine User Guide »

Once deployed in your virtual machine, we ask you to access TIRA at www.tira.io, where you can self-evaluate your software on the test data.

Note: By submitting your software you retain full copyrights. You agree to grant us usage rights only for the purpose of the PAN competition. We agree not to share your software with a third party or use it for other purposes than the PAN competition.

Results

The following table lists the performances achieved by the participating teams:

Author profiling performance
Avg. AccuracyTeam
0.5258Mart Busger op Vollenbroek, Talvany Carlotto, Tim Kreutz, Maria Medvedeva, Chris Pool, Johannes Bjerva, Hessel Haagsma, Malvina Nissim. University of Groningen, Netherlands.
0.5247Pashutan Modaresi, Matthias Liebeck, Stefan Conrad. Heinrich Heine University Düsseldorf, Germany.
0.4834Ivan Bilan, Desislava Zhekova. University of Munich, Germany.
0.4602Philipp Gross, Siavash Sefidrodi, Germany.
0.4593Ilia Markov, Helena Gómez Adorno, Grigori Sidorov, Alexander Gellbukh. Instituto Politécnico Nacional, Mexico.
0.4519Konstantinos Bougiatiotis, Anastasia Krithara. NCSR Demokritos, Greece.
0.4425Daniel Dichiu, Irina Rancea. Bitdefender, Romania.
0.4369Hannes de Valkeneer, Shoira Mukhsinova. Belgium
0.4293Waser, Switzerland (this team withdrew their submission a posteriori)
0.4255Roy Bayot, Teresa Gonçalves. Universidade de Évora, Portugal.
0.4015Pepa Gencheva, Martin Boyanov, Elena Deneva, Preslav Nakov, Yasen Kiprov, Ivan Koychev, Georgi Georgiev. Sofia University, Bulgaria.
0.4014Elena Deneva, Nikolay Hubanov. Sofia University, Bulgaria.
0.3971Madhulika Agrawal, Teresa Gonçalves. Universidade de Évora, Portugal.
0.3800Mirco Kocher, Jacques Savoy. University of Neuchâtel, Switzerland.
0.3664Constantino Román Gómez. Universidad Politécnica de Madrid, Spain.
0.3660María José Garciaren Ucelay, María Paula Villegas, Dario G. Funez, Leticia C. Cagnina, Marcelo L. Errecalde, Gabriela Ramírez de la Rosa, Esaú Villatoro Tello. Universidad Nacional de San Luis, Argentina.
0.3154Anam Zahid, Aadarsh Sampath, Anindya Dey, Golnoosh Farnady. University of Washington Tacoma, United States.
0.2949José María Aceituno. Spain.
0.1688Shaina Ashraf, Hafiz Rizwan Iqbal, Rao Muhammad Adeel Nawab. Institute of Information Technology, Pakistan.
0.1560Rodwan Bakkar Deyab, José Duarte, Teresa Gonçalves. Universidade de Évora, Portugal.
0.1410Oliver Pimas, Andi Rexha, Mark Kröll, Roman Kern. Know-Center GmbH, Austria.
0.0571Anand Kumar M., Sanjay S. Poongunran. Amrita Vishwa Vidyapeetham, India.
Related Work and Corpora

We refer you to:

Task Chair

Paolo Rosso

Paolo Rosso

Universitat Politècnica de València

Task Committee

Francisco Rangel

Francisco Rangel

Autoritas Consulting

Benno Stein

Benno Stein

Bauhaus-Universität Weimar

Martin Potthast

Martin Potthast

Bauhaus-Universität Weimar

Walter Daelemans

Walter Daelemans

University of Antwerp

Efstathios Stamatatos

Efstathios Stamatatos

University of the Aegean

© pan.webis.de