Releases: litrl/litrl_code
Litrl Browser Experimental 0.15.0.1b Public
This updates CefSharp to the latest version for security fixes.
Known issues:
- text with special characters may not be highlighted correctly by the browser when it is classified
- Certain UI widgets may not appear in the correct positions.
- column names for satire/falsification do not match data in datasets
- javascript garbage may be passed into the detectors (solution: select the text you want to process)
- The detectors may not process text content if it is loaded dynamically (solution: select the text you want to process)
- Falsifications ML model needs improvements and is the weakest of the 3
The Litrl (pronouned "literal") Browser is a research tool for news readers, journalists, editors or information professionals. The tool analyzes the language used in digital news web pages to determine if they are clickbait, satirical news, or falsified news. The current online news environment is one that incentivizes speed and spectacle in reporting at the cost of fact-checking and verification, encouraging the proliferation of misinformation and disinformation. The LiT.RL News Verification (NV) Browser is a system that offers a first step counter-measure by automatically detecting and highlighting clickbait (to 94% accuracy on a test set of 5670 texts), satire (to 84% accuracy on a test set of 95 texts), and falsified text (to 71% accuracy on a test set of 28 texts). The browser was built to study the effectiveness of these deception detectors when applied to real-world internet use, where the accuracy of these detectors may vary considerably given the range of text online. Digital literacy is key for everyone to effectively evaluate potential misinformation online, and the Litrl Browser is NOT a replacement for that. All processing is completed on the local machine - clickbait, satirical news, and falsified news results are not sent to or from a remote server. Results may be saved locally to a standard SQLite database for further analysis. Please note that Litrl Browser is not perfect and is not always correct.
This software is pre-release quality and should be used with caution. More information can be found about detector accuracies on the Wiki - we make no claims about their overall accuracy during real-world internet use.
Please see the README file for additional information.
Prerequisites to install:
Administrator account... the installer is limited and may not work properly on local/networked accounts
If you run into issues, try installing the following first:
- VC++ 2019 redistributable: https://aka.ms/vs/17/release/vc_redist.x64.exe
- .NET 4.8 runtime: https://dotnet.microsoft.com/en-us/download/dotnet-framework/thank-you/net48-web-installer
System Requirements
Windows 10, 11.
1280x720 (720p) minimum screen resolution.
1920x1080 (1080p) recommended screen resolution.
Relatively modern quad-core 64-bit CPU.
4GB of RAM.
Litrl Browser Experimental 0.15.0.0 Public
This release upgrades the project to Python 3 from 2.7 and updates CefSharp to v81.3.100. An error saving data from the detectors to a database has also been fixed, but column names in sql for satire/falsifications may not match the feature data.
The Litrl (pronouned "literal") Browser is a research tool for news readers, journalists, editors or information professionals. The tool analyzes the language used in digital news web pages to determine if they are clickbait, satirical news, or falsified news. The current online news environment is one that incentivizes speed and spectacle in reporting at the cost of fact-checking and verification, encouraging the proliferation of misinformation and disinformation. The LiT.RL News Verification (NV) Browser is a system that offers a first step counter-measure by automatically detecting and highlighting clickbait (to 94% accuracy on a test set of 5670 texts), satire (to 84% accuracy on a test set of 95 texts), and falsified text (to 71% accuracy on a test set of 28 texts). The browser was built to study the effectiveness of these deception detectors when applied to real-world internet use, where the accuracy of these detectors may vary considerably given the range of text online. Digital literacy is key for everyone to effectively evaluate potential misinformation online, and the Litrl Browser is NOT a replacement for that. All processing is completed on the local machine - clickbait, satirical news, and falsified news results are not sent to or from a remote server. Results may be saved locally to a standard SQLite database for further analysis. Please note that Litrl Browser is not perfect and is not always correct.
This software is pre-release quality and should be used with caution. More information can be found about detector accuracies on the Wiki - we make no claims about their overall accuracy during real-world internet use.
Please see the README file for additional information.
Prerequisites to install:
Administrator account... the installer is limited and may not work properly on local/networked accounts
VC++ 2017 redistributable: https://aka.ms/vs/15/release/vc_redist.x64.exe
.NET 4.6.2 (minimum) runtime: https://dotnet.microsoft.com/download/thank-you/net462
Then you can install the Browser EXE. These dependencies are not included.
System Requirements
Windows 7, 8.1 (untested), or 10.
1280x720 (720p) minimum screen resolution.
1920x1080 (1080p) recommended screen resolution.
4:3 (Square) monitors may work but are not supported.
Relatively modern quad-core 64-bit CPU.
4GB of RAM.
Litrl Browser Experimental 0.14.0.1 Public
This release contains several improvements and fixes and also the important security update affecting WebKit based browsers.
The Litrl (pronouned "literal") Browser is a research tool for news readers, journalists, editors or information professionals. The tool analyzes the language used in digital news web pages to determine if they are clickbait, satirical news, or falsified news. The current online news environment is one that incentivizes speed and spectacle in reporting at the cost of fact-checking and verification, encouraging the proliferation of misinformation and disinformation. The LiT.RL News Verification (NV) Browser is a system that offers a first step counter-measure by automatically detecting and highlighting clickbait (to 94% accuracy on a test set of 5670 texts), satire (to 84% accuracy on a test set of 95 texts), and falsified text (to 71% accuracy on a test set of 28 texts). The browser was built to study the effectiveness of these deception detectors when applied to real-world internet use, where the accuracy of these detectors may vary considerably given the range of text online. Digital literacy is key for everyone to effectively evaluate potential misinformation online, and the Litrl Browser is NOT a replacement for that. All processing is completed on the local machine - clickbait, satirical news, and falsified news results are not sent to or from a remote server. Results may be saved locally to a standard SQLite database for further analysis. Please note that Litrl Browser is not perfect and is not always correct.
This software is pre-release quality and should be used with caution. More information can be found about detector accuracies on the Wiki - we make no claims about their overall accuracy during real-world internet use.
Please see the README file for additional information.
Prerequisites to install:
- VC++ 2017 redistributable: https://aka.ms/vs/15/release/vc_redist.x64.exe
- .NET 4.6.2 (minimum) runtime: https://dotnet.microsoft.com/download/thank-you/net462
Then you can install the Browser EXE. These dependencies are not included.
System Requirements
- Windows 7, 8.1 (untested), or 10.
- 1280x720 (720p) minimum screen resolution.
- 1920x1080 (1080p) recommended screen resolution.
- 4:3 (Square) monitors may work but are not supported.
- Relatively modern quad-core 64-bit CPU.
- 4GB of RAM.
Litrl Browser Experimental 0.12.0.0 Public
The Litrl (pronouned "literal") Browser is a research tool for news readers, journalists, editors or information professionals. The tool analyzes the language used in digital news web pages to determine if they are clickbait, satirical news, or falsified news. The current online news environment is one that incentivizes speed and spectacle in reporting at the cost of fact-checking and verification, encouraging the proliferation of misinformation and disinformation. The LiT.RL News Verification (NV) Browser is a system that offers a first step counter-measure by automatically detecting and highlighting clickbait (to 94% accuracy on a test set of 5670 texts), satire (to 84% accuracy on a test set of 95 texts), and falsified text (to 71% accuracy on a test set of 28 texts). The browser was built to study the effectiveness of these deception detectors when applied to real-world internet use, where the accuracy of these detectors may vary considerably given the range of text online. Digital literacy is key for everyone to effectively evaluate potential misinformation online, and the Litrl Browser is NOT a replacement for that. All processing is completed on the local machine - clickbait, satirical news, and falsified news results are not sent to or from a remote server. Results may be saved locally to a standard SQLite database for further analysis. Please note that Litrl Browser is not perfect and is not always correct.
This software is pre-release quality and should be used with caution. More information can be found about detector accuracies on the Wiki - we make no claims about their overall accuracy during real-world internet use.
Please see the README file for additional information.
Prerequisites to install:
- VC++ 2017 redistributable: https://aka.ms/vs/15/release/vc_redist.x64.exe
- .NET 4.6.2 (minimum) runtime: https://dotnet.microsoft.com/download/thank-you/net462
Then you can install the Browser EXE. These dependencies are not included.
System Requirements
- Windows 7, 8.1 (untested), or 10.
- 1280x720 (720p) minimum screen resolution.
- 1920x1080 (1080p) recommended screen resolution.
- 4:3 (Square) monitors may work but are not supported.
- Relatively modern quad-core 64-bit CPU.
- 4GB of RAM.