11,528 research outputs found
Overview of the Author Profiling Task at PAN 2013
Get PDF[EN] This overview presents the framework and results for the Author Profiling
task at PAN 2013. We describe in detail the corpus and its characteristics,
and the evaluation framework we used to measure the participants performance to
solve the problem of identifying age and gender from anonymous texts. Finally,
the approaches of the 21 participants and their results are described.The author profiling task @PAN-2013 was an activity of the WIQ-EI IRSES project (Grant No. 269180) within the FP 7 Marie Curie People Framework of the European Commission. We want to thank the Forensic Lab of the Universitat Pompeu Fabra Barcelona for sponsoring the award for the winner team. The work of the first author was partially funded by Autoritas Consulting SA and by Ministerio de Economía y Competitividad de España under grant ECOPORTUNITY IPT-2012-1220-430000. The work of the second author was in the framework the DIANA-APPLICATIONS-Finding Hidden Knowledge in Texts: Applications (TIN2012-38603-C02-01) project, and the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems. The work of fifth author was funded in part by the Swiss National Science Foundation (SNF) project "Mining Conversational Content for Topic Modelling and Author Identification (ChatMiner)" under grant number 200021_130208.Rangel, F.; Rosso, P.; Koppel, M.; Stamatatos, E.; Inches, G. (2013). Overview of the Author Profiling Task at PAN 2013. CLEF Conference on Multilingual and Multimodal Information Access Evaluation. 352-365. https://riunet.upv.es/handle/10251/46636S35236
Uncovering Plagiarism - Author Profiling at PAN
Get PDF[ES] PAN is a yearly workshop and evaluation lab on uncovering plagiarism, authorship, and social software misuse. Since 2009, PAN has been organizing benchmark activities on uncovering plagiarism, authorship, and social software misuse . An additional task - author profiling - has also recently been proposed. Author profiling, instead of focusing on individual authors, studies how language is shared by a class of people. Author profiling is a problem of growing importance in applications in forensics, security and marketing. For instance, a person working in the area of forensic linguistics may need to know the linguistic profile of a suspected text message (language used by a certain type of person) and identify characteristics (with language as evidence). Similarly, from a marketing viewpoint, companies may be interested in determining, through the analysis of blogs and online product reviews, what types of people like or dislike their products.Rosso, P.; Rangel Pardo, FM. (2014). Uncovering Plagiarism - Author Profiling at PAN. Ercim News. (96):49-49. https://riunet.upv.es/handle/10251/49303S49499
Overview of PAN 2018 : author identification, author profiling, and author obfuscation
Get PDFAbstract: PAN 2018 explores several authorship analysis tasks enabling a systematic comparison of competitive approaches and advancing research in digital text forensics. More specifically, this edition of PAN introduces a shared task in cross-domain authorship attribution, where texts of known and unknown authorship belong to distinct domains, and another task in style change detection that distinguishes between single-author and multi-author texts. In addition, a shared task in multimodal author profiling examines, for the first time, a combination of information from both texts and images posted by social media users to estimate their gender. Finally, the author obfuscation task studies how a text by a certain author can be paraphrased so that existing author identification tools are confused and cannot recognize the similarity with other texts of the same author. New corpora have been built to support these shared tasks. A relatively large number of software submissions (41 in total) was received and evaluated. Best paradigms are highlighted while baselines indicate the pros and cons of submitted approaches
E.: Overview of the Author Identification Task at PAN-2013
No full textAbstract. The author identification task at PAN-2014 focuses on author verification. Similar to PAN-2013 we are given a set of documents by the same author along with exactly one document of questioned authorship, and the task is to determine whether the known and the questioned documents are by the same author or not. In comparison to PAN-2013, a significantly larger corpus was built comprising hundreds of documents in four natural languages (Dutch, English, Greek, and Spanish) and four genres (essays, reviews, novels, opinion articles). In addition, more suitable performance measures are used focusing on the accuracy and the confidence of the predictions as well as the ability of the submitted methods to leave some problems unanswered in case there is great uncertainty. To this end, we adopt the c@1 measure, originally proposed for the question answering task. We received 13 software submissions that were evaluated in the TIRA framework. Analytical evaluation results are presented where one language-independent approach serves as a challenging baseline. Moreover, we continue the successful practice of the PAN labs to examine meta-models based on the combination of all submitted systems. Last but not least, we provide statistical significance tests to demonstrate the important differences between the submitted approaches.
Overview of the author identification task at PAN 2014
Get PDFThe author identification task at PAN-2014 focuses on author verification. Similar to PAN-2013 we are given a set of documents by the same author along with exactly one document of questioned authorship, and the task is to determine whether the known and the questioned documents are by the same author or not. In comparison to PAN-2013, a significantly larger corpus was built comprising hundreds of documents in four natural languages (Dutch, English, Greek, and Spanish) and four genres (essays, reviews, novels, opinion articles). In addition, more suitable performance measures are used focusing on the accuracy and the confidence of the predictions as well as the ability of the submitted methods to leave some problems unanswered in case there is great uncertainty. To this end, we adopt the c@1 measure, originally proposed for the question answering task. We received 13 software submissions that were evaluated in the TIRA framework. Analytical evaluation results are presented where one language-independent approach serves as a challenging baseline. Moreover, we continue the successful practice of the PAN labs to examine meta-models based on the combination of all submitted systems. Last but not least, we provide statistical significance tests to demonstrate the important differences between the submitted approaches
Tweet Author Gender Identification. PAN 2016 Task
Get PDFThe paper presents an experiment of tweet’s author gender detection. We used PAN 2016 data and task description and have build an application that decides whether an analysed tweet has been written by man or woman. Multiple texts’ characteristics are used as features in the application, such as: references to pictures, to web pages, to other people, emojis, hashtags and a number of words that are associated with tweets written by women and men respectively. For 100 random tweets we obtained average accuracy 0.61. This is good result although it is not as good as the best one in PAN 2016 task
Long-range and high-resolution correlation optical time-domain reflectometry using a monolithic integrated broadband chaotic laser
No full text- …
