Skip to main content
SearchLoginLogin or Signup

Toward the Automatic Identification of Isotopies

Published onDec 23, 2023
Toward the Automatic Identification of Isotopies
history

You're viewing an older Release (#1) of this Pub.

  • This Release (#1) was created on Oct 22, 2023 ()
  • The latest Release (#2) was created on Dec 22, 2023 ().

Abstract


The rise in processing power, combined with advancements in machine learning, has resulted in an increase in the use of computational methods for automated content analysis. Although human coding is more effective for handling complex variables at the core of media studies, audiovisual content is often understudied because analyzing it is difficult and time-consuming. The present work sets out to address this issue by experimenting with unimodal and multimodal transformer-based models in an attempt to automatically classify segments from the popular medical TV drama Grey's Anatomy (ABC, 2005-) into three isotopies that are typical of the medical drama genre. To approach the task, this study explores two different classification approaches: the first approach is to employ a single multiclass classifier, while the second involves using the one-vs-the-rest approach to decompose the multiclass task with a series of binary classifiers. We investigate both these approaches in unimodal and multimodal settings, with the aim of identifying the most effective combination of the two. The results of the experiments can be considered promising, as the multiclass multimodal approach results in an F1 score of 0.723, a noticeable improvement over the F1 of 0.686 obtained by the one-vs-the-rest unimodal approach based on text.

Keywords

Automated content analysis; deep learning; transformers; multimodality; Grey’s Anatomy.

Comments
0
comment
No comments here
Why not start the discussion?