Shared Tasks

Important Dates

  • March 30, 2018: Early bird software submission
  • April 15, 2018: TIRA evaluation phase opens
  • May 11, 2018: TIRA evaluation phase deadline
  • May 31, 2018 (extended): Paper submission: [template] [guidelines] [submission]
  • June 15, 2018: Peer review notification
  • June 29, 2018: Camera-ready participant papers submission
  • June 30, 2018: Early bird conference registration
  • September 10-14, 2018: Conference

The timezone of all deadlines is Anywhere on Earth.


David Losada
Profiling Depression and Anorexia in Social Media
University of Santiago de Compostela (Spain)

In this talk I will review some recent results regarding early detection of signs of depression and anorexia. Since 2017, we have been organizing eRisk, a CLEF lab that promotes the development of effective and efficient solutions for early risk prediction on the Internet. eRisk explores the evaluation methodology, effectiveness metrics and practical applications (particularly those related to health and safety) of early risk detection on the Internet. Early detection technologies can be employed in different areas, particularly those related to health and safety. For instance, early alerts could be sent when a predator starts interacting with a child for sexual purposes, or when a potential offender starts publishing antisocial threats on a blog, forum or social network. Our main goal is to pioneer a new interdisciplinary research area that would be potentially applicable to a wide variety of situations and to many different personal profiles. Examples include potential paedophiles, stalkers, individuals that could fall into the hands of criminal organisations, people with suicidal inclinations, or people susceptible to depression. In this talk, I will discuss the lessons learned over these two years and some future lines of work.

Dr. David E. Losada is an Associate Professor in Computer Science & Artificial Intelligence at the University of Santiago de Compostela (Spain). He is currently the Director of the Master's Programme on Big Data Analytics. David E. Losada received his BS in Computer Science (with honors) in 1997, and his PhD in Computer Science (with honors) in 2001, both from the University of A Coruña (Spain). From 2001 to 2002, he was a lecturer in the San Pablo-CEU University (Spain) and, in 2003, he joined the Univ. of Santiago de Compostela as a senior research fellow ("Ramón y Cajal" R&D programme). His current research interests include a wide range of Information Retrieval (IR) and related areas such as: early risk detection, text mining, IR evaluation, IR probabilistic models, summarization, novelty detection, and sentence retrieval. Losada is an active member of the IR community and he regularly serves in the Programme Committee of prestigious international conferences such as SIGIR or ECIR. He has also led several R&D projects and contracts in the area of search technologies. In 2011, Losada was recognized with an ACM senior member award. David started the organization of eRisk in 2017. eRisk is a CLEF lab that promotes the development of effective and efficient solutions for early risk prediction on the Internet.

Read more… Read less…
Aleksandr Farseev
Demystifying Psychometric Marketing: Multi-View Learning as a New Social Media User Profiling Standard

The drastic change in the Web was witnessed throughout the past decade, which saw an exponential growth in social networking services. Traditionally, social network users are encouraged to complete their profiles by explicitly providing their personal attributes such as age, gender, interests, etc. Such information is essential for Marketing, Facility Arrangement, or Candidate Assessment, but, unfortunately, often not publicly available. This gives rise to user profiling, which aims at automatic inference of individual user attributes based on their social network interactions. Considering that human beings frequently contribute multi-modal data in multiple online social networks at the same time, it is essential to implement inter-source complimentary multi-view learning techniques to perform automatic user profiling efficiently. In this talk, we will overview recent research attempts on learning across multiple social networks and data modalities for automatic user profiling. We will also give several practical examples of how Multi-View User Profiling helps in boosting the efficiency of enterprises' marketing efforts.

Aleksandr Farseev is an international researcher, entrepreneur and the founder of, the Social Media Marketing platform driven by AI. He has obtained his Ph.D. degree from the National University of Singapore and currently holding an Adjunct Professor position at ITMO University, Russia. Apart from academic efforts, Aleksandr leads the AI research department at - an AI-Driven Social Discovery and Influencer Marketing Platform. Aleksandr's research interests include Social Media Analytics, Multi-View Learning, and Automatic User Profiling. He is known as one of the leading experts in Multi-View User Profile Learning.

Read more… Read less…
Jahna Otterbacher
Competent Men and Warm Women: On the Detection and Origin of Gender Stereotyped Image Search Results
Open University of Cyprus & Research Centre on Interactive Media, Smart Systems & Emerging Technologies Nicosia (Cyprus)

There is much concern about algorithms that underlie information services and the view of the social world they present to users. Image search engines are known to perpetuate gender stereotypes, particularly surrounding professions (e.g., returning primarily images of men on a search for "engineer," although few, if any, men on a search for "nurse"). In the first part of the talk, I discuss the problem of detecting social biases in image search results. We developed a novel method for automatically examining the content and strength of gender stereotypes in image results, which is inspired by the trait adjective checklist method. In experiments with Microsoft Bing, we found that photos of women are more often retrieved for searches on warm character traits (e.g., "emotional"), whereas agentic traits (e.g., "rational") typically result in more images of men. In the second part of the talk, I address questions surrounding the origin of social biases in search algorithms. I will argue that the quality of image metadata is a source of bias, as algorithms are typically trained on "gold standard," human-produced metadata. Specifically, in an experiment testing a commonly used crowdsourcing task for metadata generation, I will provide evidence that people's descriptions of men and women depicted in similar contexts differ in systematic ways that are predictable by theory. In conclusion, I shall argue that while the reproduction of social stereotypes in search algorithms is likely inevitable, there are ways to effectively raise users' awareness of biases in results.

Jahna Otterbacher received her doctorate from the University of Michigan (Ann Arbor, USA), where she was a member of the Computational Linguistics and Information Retrieval (CLAIR) research group. She is currently Assistant Professor at the Open University of Cyprus (OUC), Faculty of Pure and Applied Sciences, where she is the academic coordinator of the MSc in Social Information Systems. Jahna also coordinates the Cyprus Center for Algorithmic Transparency (CyCAT) at the OUC, a new initiative funded by the H2020 Widespread Twinning program. The CyCAT seeks to promote transparency and accountability in algorithmic systems that people routinely use, but that are rather opaque to them (e.g., search engines), through three types of interventions - data-, developer- and user-focused. In addition to her post at the OUC, Jahna holds a concurrent appointment as team leader of the Transparency in Algorithms Group at RISE (Research centre on Interactive media, Smart systems and Emerging technologies), a new center of excellence and innovation in Nicosia, Cyprus, in collaboration with two international Advanced Partners, UCL and MPI.

Read more… Read less…


PAN's program is part of the CLEF conference program.

September 10
09:00-10:30 Labs Overviews
Overview of PAN 2018: Author Identification, Author Profiling, and Author Obfuscation
Efstathios Stamatatos, Francisco Rangel, Michael Tschuggnall, Benno Stein, Mike Kestemont, Paolo Rosso, Martin Potthast
11:00-12:30 Best of Labs 2017
Hierarchical Clustering Analysis: The best-performing approach at PAN 2017 author clustering task
Helena Gómez-Adorno, Carolina Martín-Del-Campo-Rodríguez, Grigori Sidorov, Yuridiana Alemán, Darnes Vilariño Ayala and David Pinto
Session 1, Chair: Paolo Rosso
14:30-15:20 Keynote: Profiling Depression and Anorexia in Social Media
David Losada
15:20-15:40 Overview of the 6th Author Profiling Task at PAN 2018: Multimodal Gender Identification in Twitter
Francisco Rangel, Paolo Rosso, Manuel Montes-y-Gómez, Martin Potthast, Benno Stein
15:40-16:00 Text and Image Synergy with Feature Cross Technique for Gender Identification
Takumi Takahashi, Takuji Tahara, Koki Nagatani, Yasuhide Miura, Tomoki Taniguchi, Tomoko Ohkuma
16:00-16:30 Break
Session 2, Chair: Francisco Rangel
16:30-16:50 Gender Identification in Twitter using N-grams and LSA
Saman Daneshvar, Diana Inkpen
16:50-17:10 Character-based Convolutional Neural Network and ResNet18 for Twitter Author Profiling
Nils Schaetti
17:10-17:50 Keynote: Demystifying Psychometric Marketing: Multi-View Learning as a New Social Media User Profiling Standard
Aleksandr Farseev
17:50-18:00 Discussion
19:00-23:00 City Tour
September 11
13:30-14:30 Poster Session
Author Profiling using Word Embeddings with Subword Information
Rafael Felipe Sandroni Dias, Ivandré Paraboni
Character-based Convolutional Neural Network for Style Change Detection
Nils Schaetti
Bidirectional Echo State Network-based Reservoir Computing for Cross-domain Authorship Attribution
Nils Schaetti
Gender Prediction From Tweets With Convolutional Neural Networks
Erhan Sezerer, Ozan Polatbilek, Özge Sevgili, Selma Tekir
CIC-GIL Approach to Cross-domain Authorship Attribution
Carolina Martín-Del-Campo-Rodríguez, Helena Gómez-Adorno, Grigori Sidorov, Ildar Batyrshin
Complexity Measures and POS n-grams for Author Identification in Several Languages
Rocío López-Anguita, Arturo Montejo-Ráez, Manuel C. Díaz-Galiano
Authorship Profiling Without Using Topical Information
Jussi Karlgren, Lewis Esposito, Chantal Gratton, Pentti Kanerva
Authorship Attribution with Neural Networks and Multiple Features
Łukasz Gągała
Stacked Gender Prediction from Tweet Texts and Images
Giovanni Ciccone, Arthur Sultan, Léa Laporte, Elöd Egyed-Zsigmond, Alaa Alhamzeh, Michael Granitzer
Gender Identification through Multi-modal Tweet Analysis using MicroTC and Bag of Visual Words
Eric S. Tellez, Sabino Miranda-Jiménez, Daniela Moctezuma, Mario Graff, Vladimir Salgado, José Ortiz-Bejar
Multi-Language Neural Network Model with Advance Preprocessor for Gender Classification over Social Media
Kashyap Raiyani, Teresa Gonçalves, Paulo Quaresma, Vítor Beires Nogueira
Multilingual Author Profiling using LSTMs
Roy Khristopher Bayot, Teresa Gonçalves
Session 3, Chair: Efstathios Stamatatos
14:30-14:50 Overview of the Author Obfuscation Task at PAN 2018: A New Approach to Measuring Safety
Martin Potthast, Felix Schremmer, Matthias Hagen, Benno Stein
14:50-15:00 UniNE at CLEF 2018: Author Masking
Mirco Kocher, Jacques Savoy
15:00-15:15 Overview of the Author Identification Task at PAN-2018: Cross-domain Authorship Attribution
Mike Kestemont, Efstathios Stamatatos, Walter Daelemans, Benno Stein, Martin Potthast
15:15-15:30 EACH-USP Ensemble Cross-domain Authorship Attribution
José Eleandro Custódio, Ivandré Paraboni
15:30-15:45 Dynamic Parameter Search for Cross-Domain Authorship Attribution
Benjamin Murauer, Michael Tschuggnall, Günther Specht
15:45-16:00 Cross-Domain Authorship Attribution Based on Compression
Oren Halvani, Lukas Graner
16:00-16:30 Break
Session 4, Chair: Mike Kestemont
16:30-17:15 Keynote: Competent Men and Warm Women: On the Detection and Origin of Gender Stereotyped Image Search Results
Jahna Otterbacher
17:15-17:30 Overview of the Author Identification Task at PAN-2018: Style Change Detection
Michael Tschuggnall, Günther Specht, Benno Stein, Martin Potthast
17:30-17:45 An Ensemble-Rich Multi-Aspect Approach Towards Robust Style Change Detection
Dimitrina Zlatkova, Daniel Kopev, Kristiyan Mitov, Atanas Atanasov, Momchil Hardalov, Ivan Koychev, Preslav Nakov
17:45-18:00 Detecting a Change of Style using Text Statistics
Kamil Safin, Aleksandr Ogaltsov
19:00-24:00 Social Event: Théâtre des Halles
September 12
08:00-10:30 Best of Labs 2017
Simply the Best: Minimalist System Trumps Complex Models in Author Profiling
Angelo Basile, Gareth Dwyer, Maria Medvedeva, Josine Rawee, Hessel Haagsma and Malvina Nissim
17:00-18:00 2019 Labs Kickoff and Closing Discussion Forum
19:00-24:00 Social Event: Théâtre des Halles & Music Festival


Organizing Committee