Loading...
Paper Number
1933
Paper Type
Completed
Description
Content analysis traditionally involves human coders manually combing through text documents to search for relevant concepts and categories. However, this approach is time-intensive and not scalable, particularly for secondary data like social media content, news articles, or corporate reports. To address this problem, the paper presents an automated framework called Automated Deductive Content Analysis of Text (ADCAT) that uses deep learning-based semantic techniques, ontology of validated construct measures, large language model, human-in-the-loop disambiguation, and a novel augmentation-based weighted contrastive learning approach for improved language representations, to build a scalable approach for deductive content analysis. We demonstrate the effectiveness of the proposed approach to identify firm innovation strategies from their 10-K reports to obtain inferences reasonably close to human coding.
Recommended Citation
De Oliveira Silveira, Alysson; Ray, Arindam; Ebrahimi, Mohammadreza; and Bhattacherjee, Anol, "Automated Deductive Content Analysis of Text: A Deep Contrastive and Active Learning Based Approach" (2023). ICIS 2023 Proceedings. 7.
https://aisel.aisnet.org/icis2023/generalis/generalis/7
Automated Deductive Content Analysis of Text: A Deep Contrastive and Active Learning Based Approach
Content analysis traditionally involves human coders manually combing through text documents to search for relevant concepts and categories. However, this approach is time-intensive and not scalable, particularly for secondary data like social media content, news articles, or corporate reports. To address this problem, the paper presents an automated framework called Automated Deductive Content Analysis of Text (ADCAT) that uses deep learning-based semantic techniques, ontology of validated construct measures, large language model, human-in-the-loop disambiguation, and a novel augmentation-based weighted contrastive learning approach for improved language representations, to build a scalable approach for deductive content analysis. We demonstrate the effectiveness of the proposed approach to identify firm innovation strategies from their 10-K reports to obtain inferences reasonably close to human coding.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
02-General