Show Navigation
Notices by mangeurdenuage (mangeurdenuage@loadaverage.org), page 62
-
News of the day:
Customers are cancelling their weddings and the like for 2021 because of our president announcing that it's forbidden to reunite more than six yesterday.
Also for some weird inexplicable reasons, the banks are very difficult to phone. My father has been trying to reach them for the past three days to ask to report a loan, he never got them, and they sucked what little there was. We still can't pay the 7k+4k+ a few other taxes.
-
>All cool dogs are in Canada
That explains why you are going there.
-
Awww, you're not buying a ps5? Too bad, I guess I'll just have to play with Tyrone
-
@roka @lebronjames75 @fp
Confused.jpg
-
Sadly correct.
-
@lord @janusz
>La dose d’ajustements à faire de partout me fait peur.
Kobalt: #001B33 https://loadaverage.org/attachment/6200376
-
Back from #walk .
I'm preparing dinner.
-
I'm going outside for a #walk with my dog.
See you all later o/
-
dogirls > foxgirls > catgirls https://loadaverage.org/attachment/4044401
-
https://blog.eunomia.social/assessing-implicit-trustworthiness-based-on-users-reactions-to-claims/
>Online textual information has been increased tremendously over the years, leading to the demand of information verification. As a result, Natural Language Processing (NLP) research on tasks such as stance detection (Derczynski et al., 2017) and fact verification (Thorne et al., 2018) is gaining momentum, as an attempt to automatically identify misinformation over the social networks (e.g., Mastodon and Twitter).
To that end, within the scope of EUNOMIA a stance classification model was trained, which involves identifying the attitude of EUNOMIA-consent Mastodon users towards the truthfulness of the rumour they are discussing. In particular, transfer learning was applied to fine tune the RoBERTa (Robustly optimized BERT) model (Liu et al., 2019) using the public available dataset SemEval 2019 Subtask 7A (Gorrell et al., 2019). This dataset contains Twitter threads and each tweet (e.g., Hostage-taker in supermarket siege killed, reports say. #ParisAttacks –LINK) in the tree-structured thread is categorised into one of the following four categories:
Support: the author of the response supports the veracity of the rumour they are responding to (e.g., I’ve heard that also).
Deny: the author of the response denies the veracity of the rumour they are responding to (e.g., That’s a lie).
Query: the author of the response asks for additional evidence in relation to the veracity of the rumour they are responding to (e.g., Really?).
Comment: the author of the response makes their own comment without a clear contribution to assessing the veracity of the rumour they are responding to (e.g., True tragedy).
Our model achieved 85.1% accuracy and 62.75 % F1-score macro. Due to the fact that this dataset includes posts using arbitrary ways of language (e.g., OMG that aint right ☹) the obtained scores are not spectacular, but even so, our approach surpasses the state-of-the-art results (i.e., 81.79% accuracy and 61.87% F1-score) for this dataset (Yang et al., 2019).
The service has been containerized and will be soon integrated with the rest of the EUNOMIA platform as another useful trustworthiness indicator for the users.
-
@r @rosamonde
>I'm not sure
>6 October 2020
https://loadaverage.org/url/6200095
>Are you confident that you can always determine the trustworthiness of what you read on social media? What if you don’t know much about a topic? Can you still do it? Sign up to the decentralized chapters EUNOMIA social media platform (powered by Mastodon) and try to find out the 10 trustworthy and 10 untrustworthy posts that our mischievous researchers will inject (based on the researchers’ scientific expertise) in a discussion of decentralized technologies between 5th and 14th October. For this very specific period of time and only, your selections will be recorded centrally by us so that we determine who has got the most of these 20 correct by the end.
>Make an account here
Log in
Click on “Local” and wait a moment for the “I trust this”, “I don’t trust this” buttons to appear (might take a few moments because it’s still early version)
Decide whether you “trust” or you “don’t trust” the posts clicking the respective
>You win points for correctly marking posts as trustworthy or untrustworthy, and lose if you get them wrong. For every correct selection, you will get +1 point and for every incorrect -1 point. For the top scorers, which will be announced the week after, the University of Nicosia has prepared a range of very attractive prizes.
>In case of any tie, the winner will be the one who had the lowest average response time in their correct answers. The response time is the time difference from when one of the 20 posts was made by the researchers to the time that the participant correctly selected “I trust this” or “I don’t trust this”.
Some advice you may want to use, not only for this competition, but more widely in social media:
Be wary of popular posts. Misinformation travels a lot faster than reliable information
Be cautious of information forwarded to you through your network
Refrain from sharing based only on headline
Be wary of resharing information solely for its high novelty. Misinformation tends to be more novel.
Be wary of language that is making you feel emotional. It is designed to become viral, not to inform.
Be mindful of your emotions when reading a post. Anger makes you susceptible to partisanship.
Note that this is an early experimental version of EUNOMIA. It will be slow and the “I trust this” buttons and other EUNOMIA functionality may not appear immediately. Bare with it please for a few moments . https://loadaverage.org/attachment/4892403
-
I can't believe this is food.
-
Back from the road.
-
@solidsanek @tuxcrafting
>You can play with the bears
Isn't that what @Mitsu is gonna do in Québec ?
-
@alex @colunadoc
En comparaison, celle de GNU, quoi que.... https://loadaverage.org/attachment/3671367
-
@alex @colunadoc
Oui oui, je trouve les images sexy, les personnes pas le logiciel.
Cert, ça me donne envie de l'acheter mais bon je suis pas un débilus total heureusement.
BSD fait ça aussi et ça me donne aussi l'envie d’essayer. https://loadaverage.org/attachment/6152781
-
> https://loadaverage.org/attachment/6199447
-
> https://loadaverage.org/attachment/6199484
-
>mangeur less
Halp. https://loadaverage.org/attachment/6199483
-
@tuxcrafting @solidsanek
>forest ranger
>less thinking
Dude.....
mangeurdenuage
why.
All Jonkman Microblog content and data are available under the 
