Automated Coding and Scoring of Text: Artifact Design, Application, and Evaluation

2021 | International Conference on Information Systems | Citations: 0

Authors: Bhattacherjee, Anol; Silveira, Alysson De Oliveira

Abstract: This paper presents an artifact to automate and quantify qualitative coding of ... Expand

Abstract: This paper presents an artifact to automate and quantify qualitative coding of text documents on predefined constructs of interest. The quantified codes, similar to Likert-scaled measures in survey research, can be analyzed using statistical models. Our approach employs sentence transformers, a deep learning model to estimate semantic text similarity between text documents and predefined construct operationalizations. We demonstrate an application of our artifact by coding and scoring a sample of corporate 10-K reports for two types of organizational innovation processes: exploration and exploitation. Our artifact is a significant methodological contribution beyond manual coding of text documents, which cannot scale up to thousands or millions of documents, or word-based automated coding, which cannot capture the semantic meaning of text and cannot score text documents. Our approach offers new possibilities in mixed-mode research by integrating qualitative and quantitative methods using design science research. Collapse

Topics: knowledge representation organizational innovation innovation management Google+ extensible markup language

Methods: ontological modelling qualitative coding computational algorithm transformer model machine learning

An Institutional Perspective on Digital Transformation

2021 | International Conference on Information Systems | Citations: 1

Authors: Kriebel, Johannes; Foege, Johann Nils

Abstract: In this study, we argue and show that firms' and industries' digital transforma ... Expand

Abstract: In this study, we argue and show that firms' and industries' digital transformations follow an institutional logic. In particular, we suggest that the information technology portfolios of firms within an industry and among industries will become more similar over time, as firms seek to secure legitimacy among stakeholders. We introduce institutional intuition as the critical attribute of firms that enables them to successfully depart from the industry's information technology portfolio. To test our theorizing, we conducted a textual analysis of the 10k filings of all S&P 1500 firms from 1993 to 2018 building quantitative, longitudinal measures for different facets of digital transformation. We find that firms with greater industry similarity achieve higher performance. Yet, firms that diverge from the industry and have the right institutional intuition can break out of this logic and achieve superior performance. Collapse

Topics: digital transformation business model organizational productivity innovation management digital innovation

Methods: theory development qualitative content analysis word embedding longitudinal research Compustat

Theories: institutional theory institutional isomorphism theory

RETRACTED: Sentiment Analysis in Decision Sciences Research: An Illustration to IT Governance

2013 | Decision Support Systems | Citations: 1

Authors: Cao, Qing; Thompson, Mark A.; Yu, Yang

Abstract: This article has been retracted: please see Elsevier Policy on Article Withdrawa ... Expand

Abstract: This article has been retracted: please see Elsevier Policy on Article Withdrawal (http://www.elsevier.com/locate/withdrawalpolicy). This article has been retracted at the request of the Authors. This article contains significant overlap with a paper submitted two months prior to this submission. (The aforementioned paper is still in pre-acceptance stage, so does not yet have citation details or DOI.) Furthermore, this article contains empirical errors. The authors would like to apologize to the readers of the journal for the inconvenience. Collapse

Topics: IT governance organizational productivity IT alignment Wikipedia COBIT

Methods: sentiment analysis classification method machine learning naïve bayes SEC EDGAR