The SHAZAAM project aims to combat misinformation targeted at Generation Z through the integration of state-of-the-art technological tools. Evidence from the literature indicates that misinformation videos share common emotional patterns. Automated models using machine learning have shown promise in identifying misinformation in videos, particularly focusing on the emotional content of the audio. This research proposes a hierarchical classification approach that classifies audio segments extracted from short social media videos into music, speech, and other categories. On a second level, it applies music and speech sentiment analysis models trained on benchmark datasets. The functionality is offered as a web application to the end-user. A prototype of the application is presented.
(See document for exact affiliation information.)
https://aes2.org/publications/elibrary-page/?id=22589
(416KB)
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member Join the AES. If you need to check your member status, login to the Member Portal.
