Slashdot Mirror
Domain: uni-weimar.de
Stories and comments across the archive that link to uni-weimar.de.
Stories · 12
-
Can Author Obfuscation Trump Forensic Linguistics? (webis.de)
An anonymous reader writes: Everyone possesses their own writing style, which may be used to identify authors even if they wish to remain anonymous: linguists employ stylometry to settle disputes over the authorship of historic texts as well as more recent cases, and are called to verify the authors of suicide notes or threatening letters. Computer linguists carry out research on software for forensic text analyses, and a recent study shows many of these approaches to be reproducible. Now, a competition has been announced to develop obfuscation software to hide an author's style with the task: "Given a document, paraphrase it so that its writing style does not match that of its original author, anymore." We'll see what comes out of that. Meanwhile, the question remains: Who will win in the long run? Forensic linguists, or obfuscation technology? -
Why Your Online Impersonation of a 16-year Old Girl Won't Last Long
An anonymous reader writes "Can computers pick up your age and gender from your tweets? If you want to give it a try, here's your chance: 'To develop your software for age and gender identification, we provide you with a training data set that consists of blog posts, Twitter tweets, social media texts, as well as hotel reviews.' Well, at least my paid Amazon reviews are safe for the time being..." -
When Writing, How Anonymous Can You Be, Really?
An anonymous reader writes "Do you still think your online writing is, basically, anonymous? Think again! Research has it people put much of their personal traits into their writing, and computers may just be able to pick them up. That's at least what a recently announced competition on author identification (Given a document, who wrote it?) and author profiling (Given a document, what are its author's age and gender?) wants to find out. Alas, re-using other people's writing is no solution either; there's also a competition on plagiarism detection (Given a document, is it an original?). Wanna revisit your recent rants?" -
When Writing, How Anonymous Can You Be, Really?
An anonymous reader writes "Do you still think your online writing is, basically, anonymous? Think again! Research has it people put much of their personal traits into their writing, and computers may just be able to pick them up. That's at least what a recently announced competition on author identification (Given a document, who wrote it?) and author profiling (Given a document, what are its author's age and gender?) wants to find out. Alas, re-using other people's writing is no solution either; there's also a competition on plagiarism detection (Given a document, is it an original?). Wanna revisit your recent rants?" -
When Writing, How Anonymous Can You Be, Really?
An anonymous reader writes "Do you still think your online writing is, basically, anonymous? Think again! Research has it people put much of their personal traits into their writing, and computers may just be able to pick them up. That's at least what a recently announced competition on author identification (Given a document, who wrote it?) and author profiling (Given a document, what are its author's age and gender?) wants to find out. Alas, re-using other people's writing is no solution either; there's also a competition on plagiarism detection (Given a document, is it an original?). Wanna revisit your recent rants?" -
Competition To Identify Sexual Predators In Chat Logs
An anonymous reader writes "Researchers from the University of Lugano, Switzerland, and other universities from the U.S. and Europe organize a competition to automatically identify sexual predators in chat logs. The task is described as: 'The goal of this sub-task is to identify classes of authors, namely online predators. You will be given chat logs involving two (or more) people and have to determine who is the one trying to convince the other participants(s) to provide some sexual favor. You will also need to identify the particular conversation where the person exploits his bad behavior.' Their data set covers hundreds of chat logs with dozens of true positives (i.e., chats where one is trying to hit on another)." -
Competition Produces Vandalism Detection For Wikis
marpot writes "Recently, the 1st International Competition on Wikipedia Vandalism Detection (PDF) finished: 9 groups (5 from the USA, 1 affiliated with Google) tried their best in detecting all vandalism cases from a large-scale evaluation corpus. The winning approach (PDF) detects 20% of all vandalism cases without misclassifying regular edits; moreover, it can be adjusted to detect 95% of the vandalism edits while misclassifying only 30% of all regular edits. Thus, by applying both settings, manual double-checking would only be required on 34% of all edits. Nothing is known, yet, whether the rule-based bots on Wikipedia can compete with this machine learning-based strategy. Anyway, there is still a lot potential for improvements since the top 2 detectors use entirely different detection paradigms: the first analyzes an edit's content, whereas the second (PDF) analyzes an edit's context using WikiTrust." -
Competition Produces Vandalism Detection For Wikis
marpot writes "Recently, the 1st International Competition on Wikipedia Vandalism Detection (PDF) finished: 9 groups (5 from the USA, 1 affiliated with Google) tried their best in detecting all vandalism cases from a large-scale evaluation corpus. The winning approach (PDF) detects 20% of all vandalism cases without misclassifying regular edits; moreover, it can be adjusted to detect 95% of the vandalism edits while misclassifying only 30% of all regular edits. Thus, by applying both settings, manual double-checking would only be required on 34% of all edits. Nothing is known, yet, whether the rule-based bots on Wikipedia can compete with this machine learning-based strategy. Anyway, there is still a lot potential for improvements since the top 2 detectors use entirely different detection paradigms: the first analyzes an edit's content, whereas the second (PDF) analyzes an edit's context using WikiTrust." -
Competition Produces Vandalism Detection For Wikis
marpot writes "Recently, the 1st International Competition on Wikipedia Vandalism Detection (PDF) finished: 9 groups (5 from the USA, 1 affiliated with Google) tried their best in detecting all vandalism cases from a large-scale evaluation corpus. The winning approach (PDF) detects 20% of all vandalism cases without misclassifying regular edits; moreover, it can be adjusted to detect 95% of the vandalism edits while misclassifying only 30% of all regular edits. Thus, by applying both settings, manual double-checking would only be required on 34% of all edits. Nothing is known, yet, whether the rule-based bots on Wikipedia can compete with this machine learning-based strategy. Anyway, there is still a lot potential for improvements since the top 2 detectors use entirely different detection paradigms: the first analyzes an edit's content, whereas the second (PDF) analyzes an edit's context using WikiTrust." -
View-Dependent Stereoscopic Projection
obiquity writes "The Augmented Reality lab is at it again with an extension of their 'smart projector' methods. In 'Enabling View-Dependent Stereoscopic Projection in Real Environments' they demonstrate a method for point-of-view dependent 3-D image projection onto almost any surface using multiple projectors for VR/AR applications. There are still several problems that need to be solved, but how far off is this technology from a holodeck type implementation?" -
View-Dependent Stereoscopic Projection
obiquity writes "The Augmented Reality lab is at it again with an extension of their 'smart projector' methods. In 'Enabling View-Dependent Stereoscopic Projection in Real Environments' they demonstrate a method for point-of-view dependent 3-D image projection onto almost any surface using multiple projectors for VR/AR applications. There are still several problems that need to be solved, but how far off is this technology from a holodeck type implementation?" -
Projecting Video On Curved Surfaces
Jochen Bedersdorfer writes "According to golem.de, a research project in the area of Augmented Reality created a technology to project videos onto arbitrary existing screen surfaces, like wallpapered walls or window curtains. ... Quite awesome. Now I can use this ugly corner in my living room effectively."
