ramybaly / article-bias-prediction Goto Github PK
View Code? Open in Web Editor NEWLicense: Apache License 2.0
License: Apache License 2.0
Hi,
Thank you for your dataset. I just wanted to say that this dataset is slightly different from the one described in your paper.
Probably it's because you have been adding newer articles, but it would be nice to state this information in the README file.
I was trying to reproduce the experiments and, for comparability, it would be nice to be able to do this on the same exact data.
EMNLP | GitHub | |
---|---|---|
total size | 34737 | 37554 |
train (media) | 22,969 | 26,590 |
validation (media) | 5,098 | 2,356 |
test (media) | 1,200 | 1,300 |
train (random) | 26,828 | 27,978 |
validation (random) | 6,709 | 6,996 |
test (random) | 1,200 | 1,300 |
Left | ... | |
Center | ... | |
Right | ... |
Best,
Martino
Could you please share source codes for crawling and annotation @ramybaly
Thanks for the great article!
Have you considered publishing your BERT Twitter bios+Article with TLP
on the HuggingFace model hub? Would be great to have a pre-trained model for detecting political orientation of articles available for the community and can imagine that people would make good use of it. (Would also be good advertisement for your model and research :) )
Hi,
Thank you so much for your awesome research work.
I am wondering about the time of releasing the code.
Thanks in advanced and regards,
Qin
Hi,
I was curious to take a look at the data and code. Is there any predicted day it will be uploaded?
Thank you.
It's a common trend in CS research where a paper says that the data or the code will be released, and an empty repo is created to support that conclusion. This helps authors get favorable reviews, and to get accepted in prestigious conferences. Then the code or data are never released, and the authors pretend as they have never promised anything. Unfortunately, it looks like the authors of this paper might be doing just that.
Hi Ramy,
Thank u for publishing this amazing paper.
It seems in this published dataset there are 192 news sources, many more than 73 reported in paper. After manually merging some similar sources there are still more than 170 sources. I wonder if you could release the exact same dataset that is reported in the paper. Thanks a lot!
Best,
Zihao
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.