US 12,223,265 B2
Explainable propaganda detection
Preslav I. Nakov, Doha (QA); Giovanni Da San Martino, Doha (QA); and Seunghak Yu, Doha (QA)
Assigned to QATAR FOUNDATION FOR EDUCATION, SCIENCE AND COMMUNITY DEVELOPMENT, Doha (QA); and MASSACHUSETTS INSTITUTE OF TECHNOLOGY, Cambridge, MA (US)
Filed by Qatar Foundation for Education, Science and Community Development, Doha (QA); and Massachusetts Institute of Technology, Cambridge, MA (US)
Filed on Jun. 30, 2022, as Appl. No. 17/855,248.
Claims priority of provisional application 63/216,945, filed on Jun. 30, 2021.
Prior Publication US 2023/0004712 A1, Jan. 5, 2023
Int. Cl. G06F 40/205 (2020.01); G06F 3/04842 (2022.01); G06F 40/289 (2020.01)
CPC G06F 40/205 (2020.01) [G06F 3/04842 (2013.01); G06F 40/289 (2020.01)] 19 Claims
OG exemplary drawing
 
1. A method, comprising:
parsing each sentence of a plurality of sentences in an article for structural details, wherein the plurality of sentences represent a threshold number of sentences selected from a beginning of the article;
identifying, via a machine learning model, dimensional features across the plurality of sentences based on the structural details;
identifying, via the machine learning model, a propagandizing tactic demonstrated in each sentence of the plurality of sentences based on a covariance score to the propagandizing tactic and the dimensional features identified for a given sentence; and
displaying, in a user interface that includes the article, propaganda labels corresponding to the propagandizing tactic identified for each sentence of the plurality of sentences.