“He looks very real”: media, knowledge, and search-based strategies for deepfake identification
Deepfakes are a potential source of disinformation and the ability to detect them is imperative. While research focused on algorithmic detection methods, there is little work conducted on how people identify deepfakes. This research attempts to fill this gap. Using semi-structured interviews, partic...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/174650 |
| _version_ | 1811681889376796672 |
|---|---|
| author | Goh, Dion Hoe-Lian |
| author2 | Wee Kim Wee School of Communication and Information |
| author_facet | Wee Kim Wee School of Communication and Information Goh, Dion Hoe-Lian |
| author_sort | Goh, Dion Hoe-Lian |
| collection | NTU |
| description | Deepfakes are a potential source of disinformation and the ability to detect them is imperative. While research focused on algorithmic detection methods, there is little work conducted on how people identify deepfakes. This research attempts to fill this gap. Using semi-structured interviews, participants were asked to identify real and deepfake videos and explain how their decisions were made. Three categories of deepfake identification strategies emerged: the use of surface video and audio cues, processing of the messages conveyed in the video, and the searching of external sources. Participants often used multiple strategies within each category. However, identification challenges occurred due to participants' preconceived notions of deepfake characteristics and the message embodied in the video. This work contributes to research by shifting the focus from the algorithmic detection of deepfakes to human-oriented strategies. Practically, the findings provide guidance on how people can identify deepfakes, which can also form the basis for the development of educational materials. |
| first_indexed | 2024-10-01T03:48:07Z |
| format | Journal Article |
| id | ntu-10356/174650 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:48:07Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1746502024-04-07T15:33:29Z “He looks very real”: media, knowledge, and search-based strategies for deepfake identification Goh, Dion Hoe-Lian Wee Kim Wee School of Communication and Information Arts and Humanities Disinformation Human experiment Deepfakes are a potential source of disinformation and the ability to detect them is imperative. While research focused on algorithmic detection methods, there is little work conducted on how people identify deepfakes. This research attempts to fill this gap. Using semi-structured interviews, participants were asked to identify real and deepfake videos and explain how their decisions were made. Three categories of deepfake identification strategies emerged: the use of surface video and audio cues, processing of the messages conveyed in the video, and the searching of external sources. Participants often used multiple strategies within each category. However, identification challenges occurred due to participants' preconceived notions of deepfake characteristics and the message embodied in the video. This work contributes to research by shifting the focus from the algorithmic detection of deepfakes to human-oriented strategies. Practically, the findings provide guidance on how people can identify deepfakes, which can also form the basis for the development of educational materials. Ministry of Education (MOE) Submitted/Accepted version This research was supported by a Ministry of Education(Singapore) Tier 2 grant (MOE-T2EP40122-004). 2024-04-07T01:11:14Z 2024-04-07T01:11:14Z 2024 Journal Article Goh, D. H. (2024). “He looks very real”: media, knowledge, and search-based strategies for deepfake identification. Journal of the Association for Information Science and Technology. https://dx.doi.org/10.1002/asi.24867 2330-1635 https://hdl.handle.net/10356/174650 10.1002/asi.24867 2-s2.0-85181503417 en Journal of the Association for Information Science and Technology © 2024 Association for Information Science and Technology. All rights reserved. This article may be downloaded for personal use only. Any other use requires prior permission of the copyright holder. The Version of Record is available online at http://doi.org/10.1002/asi.24867. application/pdf |
| spellingShingle | Arts and Humanities Disinformation Human experiment Goh, Dion Hoe-Lian “He looks very real”: media, knowledge, and search-based strategies for deepfake identification |
| title | “He looks very real”: media, knowledge, and search-based strategies for deepfake identification |
| title_full | “He looks very real”: media, knowledge, and search-based strategies for deepfake identification |
| title_fullStr | “He looks very real”: media, knowledge, and search-based strategies for deepfake identification |
| title_full_unstemmed | “He looks very real”: media, knowledge, and search-based strategies for deepfake identification |
| title_short | “He looks very real”: media, knowledge, and search-based strategies for deepfake identification |
| title_sort | he looks very real media knowledge and search based strategies for deepfake identification |
| topic | Arts and Humanities Disinformation Human experiment |
| url | https://hdl.handle.net/10356/174650 |
| work_keys_str_mv | AT gohdionhoelian helooksveryrealmediaknowledgeandsearchbasedstrategiesfordeepfakeidentification |