We have published the app in the Android Play Store: Logical Fallacy Detector App This screenshot was taken when the app was just published, so download count is just 1. Detecting Logical Fallacies The main screen of the app allows to type in any text max 500 letters long. Then after the button Detect is pressed the app sends the text for the analysis to the cloud, receives the detection result with the list of found logical fallacies and shows them under the text.
News and Articles
How We Choose We haveve selected the top most engaging news articles on Twitter from Australian MSM and prominent journalists. The selection criteria are based on logical fallacies statistics found in the retweets and comments. Critical Concentration “Prince Harry should dump his salacious tell-all and rein in Meghan Markle if he wants to honour King Charles, writes Piers Morgan.” The response to this tweet from Sky News Australia contains approximately 62% of comments that look a lot like fallacious reasoning of any type our detector can recognise.
Appeal to Ignorance comes from argumentum ad ignorantiam, which is a Latin word that literally translates as “Argument from ignorance.” This is the logical fallacy that a statement or belief is false simply because it has not been proven true or, conversely, true because it has not been proven false. This is a variation of “innocent until proven guilty” that resonates so well in America because it is what American criminal justice system is based upon.
Logical Fallacy Detector and Dataset A new paper published in Feb 2022 (v1) - May 2022 (v2) “Logical Fallacy Detector” by Zhijing Jin and others, has a dataset “Logic” of annotated logical fallacy examples as an open-source appendix. This dataset is available on https://github.com/causalNLP/logical-fallacy . In case the original repo is not online - the Sep 2022 copy of the repository is available on https://github.com/tmakesense/logical-fallacy/tree/main/original-logical-fallacy-by-causalNLP . This publication arxiv:2202.13758 has on the top of the annotation page Below is the original cleaning process described in the citation from the paper, section A.