A Decade of Shared Tasks in Digital Text Forensics at PAN

Potthast, Martin; Rosso, Paolo; Stamatatos, Efstathios; Stein, Benno

doi:10.1007/978-3-030-15719-7_39

Cited by 12 publications

(10 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notably, the PAN au-thor profiling shared task (Rangel et al, 2013(Rangel et al, , 2014Rangel Pardo et al, 2015;Rangel et al, 2016Rangel et al, , 2017 was launched to progress work in this area. A summary of the PAN work can be found in (Potthast et al, 2019)…”

Section: Author Profilingmentioning

confidence: 99%

Sentence-Level BERT and Multi-Task Learning of Age and Gender in Social Media

Abdul-Mageed¹,

Zhang²,

Rajendran³

et al. 2019

Preprint

View full text Add to dashboard Cite

Social media currently provide a window on our lives, making it possible to learn how people from different places, with different backgrounds, ages, and genders use language. In this work we exploit a newly-created Arabic dataset with ground truth age and gender labels to learn these attributes both individually and in a multi-task setting at the sentence level. Our models are based on variations of deep bidirectional neural networks. More specifically, we build models with gated recurrent units and bidirectional encoder representations from transformers (BERT). We show the utility of multi-task learning (MTL) on the two tasks and identify taskspecific attention as a superior choice in this context. We also find that a single-task BERT model outperform our best MTL models on the two tasks. We report tweet-level accuracy of 51.43% for the age task (three-way) and 65.30% on the gender task (binary), both of which outperforms our baselines with a large margin. Our models are languageagnostic, and so can be applied to other languages.

show abstract

Section: Author Profilingmentioning

confidence: 99%

Sentence-Level BERT and Multi-Task Learning of Age and Gender in Social Media

Abdul-Mageed¹,

Zhang²,

Rajendran³

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…In addition, the PAN author profiling shared task [34,33,37,36,35] was established to advance related work. More information about PAN can be found in [29].…”

Section: Related Workmentioning

confidence: 99%

BERT-Based Arabic Social Media Author Profiling

Zhang,

Abdul-Mageed

2019

Preprint

View full text Add to dashboard Cite

We report our models for detecting age, language variety, and gender from social media data in the context of the Arabic author profiling and deception detection shared task (APDA) [32]. We build simple models based on pre-trained bidirectional encoders from transformers (BERT). We first fine-tune the pre-trained BERT model on each of the three datasets with shared task released data. Then we augment shared task data with in-house data for gender and dialect, showing the utility of augmenting training data. Our best models on the shared task test data are acquired with a majority voting of various BERT models trained under different data conditions. We acquire 54.72% accuracy for age, 93.75% for dialect, 81.67% for gender, and 40.97% joint accuracy across the three tasks.

show abstract

“…Digital text forensics aims at examining the originality and credibility of information in electronic documents and, in this regard, at extracting and analyzing information about the authors of the respective texts [30]. Among the most important tasks of this field are authorship attribution (AA) and authorship verification (AV), where the former deals with the problem of identifying the most likely author of a document D U with unknown authorship, given a set of texts of candidate authors.…”

Section: Introductionmentioning

confidence: 99%

Assessing the Applicability of Authorship Verification Methods

Halvani

Winter

Graner

2019

Proceedings of the 14th International Conference on Availability, Reliability and Security

View full text Add to dashboard Cite

Authorship verification (AV) is a research subject in the field of digital text forensics that concerns itself with the question, whether two documents have been written by the same person. During the past two decades, an increasing number of proposed AV approaches can be observed. However, a closer look at the respective studies reveals that the underlying characteristics of these methods are rarely addressed, which raises doubts regarding their applicability in real forensic settings. The objective of this paper is to fill this gap by proposing clear criteria and properties that aim to improve the characterization of existing and future AV approaches. Based on these properties, we conduct three experiments using 12 existing AV approaches, including the current state of the art. The examined methods were trained, optimized and evaluated on three self-compiled corpora, where each corpus focuses on a different aspect of applicability. Our results indicate that part of the methods are able to cope with very challenging verification cases such as 250 characters long informal chat conversations (72.7% accuracy) or cases in which two scientific documents were written at different times with an average difference of 15.6 years (> 75% accuracy). However, we also identified that all involved methods are prone to cross-topic verification cases.

show abstract

A Decade of Shared Tasks in Digital Text Forensics at PAN

Cited by 12 publications

References 20 publications

Sentence-Level BERT and Multi-Task Learning of Age and Gender in Social Media

Sentence-Level BERT and Multi-Task Learning of Age and Gender in Social Media

BERT-Based Arabic Social Media Author Profiling

Assessing the Applicability of Authorship Verification Methods

Contact Info

Product

Resources

About