Hi everyone,
we [1] would like to announce a research project with the goal of studying whether user interactions recorded at the time of editing are suitable to predict vandalism in real time.
Should vandal editing behavior be sufficiently different from normal editing behavior, this would allow for a number of interesting real-time prevention techniques. For example: - withholding confidently suspicious edits for review before publishing them, - a popup asking "I am not a vandal" (as in Google's "I am not a robot") to analyze vandal reactions, - a popup with a chat box to personally engage vandals, e.g., to help them find other ways of stress relief or to understand them better, - or at the very least: a new signal to improve traditional vandalism detectors.
We have set up a laboratory environment to study editor behavior in a realistic setting using a private mirror of Wikipedia. No editing whatsoever is conducted on the real Wikipedia as part of our experiments, and all test subjects of our user studies are made aware of the experimental nature of their editing. We plan on making use of crowdsourcing as a means to attain scale and diversity.
If you wish to participate in this study as a test subject yourself, please get in touch. The more diversity, the more insightful the results will be. We are also happy to collaborate and to answer all questions that may arise in relation to the project. For example, our setup and tooling may turn out to be useful to study other user behavior-related things without having to actually deploy experiments within the live MediaWiki.
Best, Martin
PS: The AICaptcha project seems most closely related. @Vinitha and Gergő: If you wish, we can set up a Skype meeting to talk about a avenues for collaboration.
[1] A group of students and researchers from Bauhaus-Universität Weimar ( www.webis.de) and Leipzig University (www.temir.org); project PI: Martin Potthast.
Hi Martin,
Thanks for the update. I'm very interested to learn more once you have more to share.
I'm not sure if you're aware of the research on sockpuppet detection. It's a different problem than what you describe here, but I would not be surprised if learnings from each of these projects can help another. You can keep in touch with the sockpuppet detection at https://meta.wikimedia.org/wiki/Research:Sockpuppet_detection_in_Wikimedia_p...
Also, if you will have early results, feel free to submit them as part of the March 11 deadline (http://wikiworkshop.org/2018/#dates) for Wiki Workshop. It would be great to have a chance to discuss this research more in person if you or your team will end up being in Lyon for TWC2019.
Best, Leila
On Sat, Jan 20, 2018 at 2:39 AM, Martin Potthast martin.potthast@uni-leipzig.de wrote:
Hi everyone,
we [1] would like to announce a research project with the goal of studying whether user interactions recorded at the time of editing are suitable to predict vandalism in real time.
Should vandal editing behavior be sufficiently different from normal editing behavior, this would allow for a number of interesting real-time prevention techniques. For example:
- withholding confidently suspicious edits for review before publishing
them,
- a popup asking "I am not a vandal" (as in Google's "I am not a robot") to
analyze vandal reactions,
- a popup with a chat box to personally engage vandals, e.g., to help them
find other ways of stress relief or to understand them better,
- or at the very least: a new signal to improve traditional vandalism
detectors.
We have set up a laboratory environment to study editor behavior in a realistic setting using a private mirror of Wikipedia. No editing whatsoever is conducted on the real Wikipedia as part of our experiments, and all test subjects of our user studies are made aware of the experimental nature of their editing. We plan on making use of crowdsourcing as a means to attain scale and diversity.
If you wish to participate in this study as a test subject yourself, please get in touch. The more diversity, the more insightful the results will be. We are also happy to collaborate and to answer all questions that may arise in relation to the project. For example, our setup and tooling may turn out to be useful to study other user behavior-related things without having to actually deploy experiments within the live MediaWiki.
Best, Martin
PS: The AICaptcha project seems most closely related. @Vinitha and Gergő: If you wish, we can set up a Skype meeting to talk about a avenues for collaboration.
[1] A group of students and researchers from Bauhaus-Universität Weimar ( www.webis.de) and Leipzig University (www.temir.org); project PI: Martin Potthast. _______________________________________________ Wiki-research-l mailing list Wiki-research-l@lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/wiki-research-l
Hi Leila,
thanks for the pointers! We've already been in touch with Vinitha, Gergő, and Adam, talking about potential points of connecting the two projects. I will look into the Sockpuppet detection project. About the workshop, I'm not sure if we can manage to write up something by the time of the deadline.
Martin
On Mon, Feb 12, 2018 at 8:41 PM, Leila Zia leila@wikimedia.org wrote:
Hi Martin,
Thanks for the update. I'm very interested to learn more once you have more to share.
I'm not sure if you're aware of the research on sockpuppet detection. It's a different problem than what you describe here, but I would not be surprised if learnings from each of these projects can help another. You can keep in touch with the sockpuppet detection at https://meta.wikimedia.org/wiki/Research:Sockpuppet_ detection_in_Wikimedia_projects
Also, if you will have early results, feel free to submit them as part of the March 11 deadline (http://wikiworkshop.org/2018/#dates) for Wiki Workshop. It would be great to have a chance to discuss this research more in person if you or your team will end up being in Lyon for TWC2019.
Best, Leila
On Sat, Jan 20, 2018 at 2:39 AM, Martin Potthast martin.potthast@uni-leipzig.de wrote:
Hi everyone,
we [1] would like to announce a research project with the goal of
studying
whether user interactions recorded at the time of editing are suitable to predict vandalism in real time.
Should vandal editing behavior be sufficiently different from normal editing behavior, this would allow for a number of interesting real-time prevention techniques. For example:
- withholding confidently suspicious edits for review before publishing
them,
- a popup asking "I am not a vandal" (as in Google's "I am not a robot")
to
analyze vandal reactions,
- a popup with a chat box to personally engage vandals, e.g., to help
them
find other ways of stress relief or to understand them better,
- or at the very least: a new signal to improve traditional vandalism
detectors.
We have set up a laboratory environment to study editor behavior in a realistic setting using a private mirror of Wikipedia. No editing whatsoever is conducted on the real Wikipedia as part of our experiments, and all test subjects of our user studies are made aware of the experimental nature of their editing. We plan on making use of crowdsourcing as a means to attain scale and diversity.
If you wish to participate in this study as a test subject yourself,
please
get in touch. The more diversity, the more insightful the results will
be.
We are also happy to collaborate and to answer all questions that may
arise
in relation to the project. For example, our setup and tooling may turn
out
to be useful to study other user behavior-related things without having
to
actually deploy experiments within the live MediaWiki.
Best, Martin
PS: The AICaptcha project seems most closely related. @Vinitha and Gergő: If you wish, we can set up a Skype meeting to talk about a avenues for collaboration.
[1] A group of students and researchers from Bauhaus-Universität Weimar ( www.webis.de) and Leipzig University (www.temir.org); project PI: Martin Potthast. _______________________________________________ Wiki-research-l mailing list Wiki-research-l@lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/wiki-research-l
Wiki-research-l mailing list Wiki-research-l@lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/wiki-research-l
On Feb 15, 2018 03:20, "Martin Potthast" martin.potthast@uni-weimar.de wrote:
Hi Leila,
thanks for the pointers! We've already been in touch with Vinitha, Gergő, and Adam, talking about potential points of connecting the two projects.
Great. :)
I will look into the Sockpuppet detection project. About the workshop, I'm not sure if we can manage to write up something by the time of the deadline.
You are not stranger to the workshop ;) but just to emphasize: the submissions can be about ideas, work-in-progress, or completed research, anywhere from 2-8 pages long. No pressure, of course. :)
Srijan is telling me it's very likely he will be there in the workshop (in the conference for sure). If you end up joining us, we can have some f2f chat about this as well, which is always nice. :)
Leila
Martin
On Mon, Feb 12, 2018 at 8:41 PM, Leila Zia leila@wikimedia.org wrote:
Hi Martin,
Thanks for the update. I'm very interested to learn more once you have more to share.
I'm not sure if you're aware of the research on sockpuppet detection. It's a different problem than what you describe here, but I would not be surprised if learnings from each of these projects can help another. You can keep in touch with the sockpuppet detection at https://meta.wikimedia.org/wiki/Research:Sockpuppet_ detection_in_Wikimedia_projects
Also, if you will have early results, feel free to submit them as part of the March 11 deadline (http://wikiworkshop.org/2018/#dates) for Wiki Workshop. It would be great to have a chance to discuss this research more in person if you or your team will end up being in Lyon for TWC2019.
Best, Leila
On Sat, Jan 20, 2018 at 2:39 AM, Martin Potthast martin.potthast@uni-leipzig.de wrote:
Hi everyone,
we [1] would like to announce a research project with the goal of
studying
whether user interactions recorded at the time of editing are suitable
to
predict vandalism in real time.
Should vandal editing behavior be sufficiently different from normal editing behavior, this would allow for a number of interesting real-time prevention techniques. For example:
- withholding confidently suspicious edits for review before publishing
them,
- a popup asking "I am not a vandal" (as in Google's "I am not a robot")
to
analyze vandal reactions,
- a popup with a chat box to personally engage vandals, e.g., to help
them
find other ways of stress relief or to understand them better,
- or at the very least: a new signal to improve traditional vandalism
detectors.
We have set up a laboratory environment to study editor behavior in a realistic setting using a private mirror of Wikipedia. No editing whatsoever is conducted on the real Wikipedia as part of our
experiments,
and all test subjects of our user studies are made aware of the experimental nature of their editing. We plan on making use of crowdsourcing as a means to attain scale and diversity.
If you wish to participate in this study as a test subject yourself,
please
get in touch. The more diversity, the more insightful the results will
be.
We are also happy to collaborate and to answer all questions that may
arise
in relation to the project. For example, our setup and tooling may turn
out
to be useful to study other user behavior-related things without having
to
actually deploy experiments within the live MediaWiki.
Best, Martin
PS: The AICaptcha project seems most closely related. @Vinitha and
Gergő:
If you wish, we can set up a Skype meeting to talk about a avenues for collaboration.
[1] A group of students and researchers from Bauhaus-Universität Weimar
(
www.webis.de) and Leipzig University (www.temir.org); project PI: Martin Potthast. _______________________________________________ Wiki-research-l mailing list Wiki-research-l@lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/wiki-research-l
Wiki-research-l mailing list Wiki-research-l@lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/wiki-research-l
-- Dr. Martin Potthast Bauhaus-Universität Weimar Digital Bauhaus Lab Bauhausstr. 9a 99423 Weimar Germany
+49 3643 58 3567 +49 171 809 1945
www.potthast.net _______________________________________________ Wiki-research-l mailing list Wiki-research-l@lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/wiki-research-l
wiki-research-l@lists.wikimedia.org