International Journal of Accounting Information Systems最新文献

We investigate the feasibility of machine learning methods for attributional content and framing analysis in corporate reporting. We test the performance of five widely-used supervised machine learning classifiers (naïve Bayes, logistic regression, support vector machines, random forests, decision trees) in a top-down three-level hierarchical setting to (1) identify performance-related statements; (2) detect attributions in these; and (3) classify the content of the attributional statements. The training set comprises manually coded statements from a corpus of management commentary reports of listed companies. The attributions include both intra- and inter-sentential attributional statements. The results show that for both intra- and inter-sentential attributions, F1-scores of our most accurate classifier (i.e., support vector machines) vary in the range of 76% up to 94%, depending on the identification, detection and classification levels and the content characteristics of attributions. Additionally, we assess the hierarchical performance of classifiers, providing insights into a more holistic classification process for attributional statements. Overall, our results show how machine learning methods may facilitate narrative disclosure analysis by providing a more efficient way to detect and classify performance-related attributional statements. Our findings contribute to the accounting and management literature by providing a basis for implementing machine learning methodologies for research investigating attributional behavior and related impression management.

We examine the effects of information technology material weaknesses on a firm’s reputation by examining how management’s actions before and after disclosure influence investors’ trust in management and perceptions of investment risk. Specifically, we look at the influence of: 1) management taking responsibility for an information technology material weakness, and 2) replacing the CFO with someone with technology expertise. We find that management taking responsibility for a material weakness does not lead to increased trust in management before or after remediation. However, investors perceive more favorable market reactions to remediation when management had previously taken responsibility for the control weakness. Further, we find that replacing the CFO with someone who has technology expertise results in increases in investor trust and improvements in perceptions of investment risk after control weakness remediation. This suggests the importance of sending clear signals to investors that the company is hiring managers with appropriate technology expertise.

This study demonstrates a way of bringing an innovative data source, social media information, to the government accounting information systems to support accountability to stakeholders and managerial decision-making. Future accounting and auditing processes will heavily rely on multiple forms of exogenous data. As an example of the techniques that could be used to generate this needed information, the study applies text mining techniques and machine learning algorithms to Twitter data. The information is developed as an alternative performance measure for NYC street cleanliness. It utilizes Naïve Bayes, Random Forest, and XGBoost to classify the tweets, illustrates how to use the sampling method to solve the imbalanced class distribution issue, and uses VADER sentiment to derive the public opinion about street cleanliness. This study also extends the research to another social media platform, Facebook, and finds that the incremental value is different between the two social media platforms. This data can then be linked to government accounting information systems to evaluate costs and provide a better understanding of the efficiency and effectiveness of operations.

A key advantage of conceptual models is that their quality can be evaluated and validated before beginning the costlier stages of information system development. Few research studies investigate the validation process for such models, particularly regarding multiplicities, even though multiplicity mistakes can be very costly. We investigated the validation of conceptual model multiplicities, varying how closely natural language statements of business rules match the models that purport to represent those rules. Participants in an eye tracking experiment completed validation tasks in which they viewed a statement and an accompanying UML class diagram in which a specified multiplicity was consistent with the statement (valid) or inconsistent with the statement (invalid). We varied whether the focal multiplicity was a minimum or a maximum and varied the class diagram’s semantics and order compared to that of the statement. Logistic regression was used to analyze the relationship between accuracy and the experimental manipulations and controls. The results show that the odds of accuracy in validating class diagrams that used synonyms instead of the exact statement terminology were only 0.46 times the odds of accuracy when the class diagram and statement words matched, showing a costly effect of synonymy. Interestingly, independent of the three levels of relative semantics, the odds of accuracy were 0.48 times when class diagrams were consistent with business rules as they were when class diagrams were inconsistent with business rules. To gain insight into cognition under correct task performance, we conducted additional linear regression analysis on various eye tracking metrics for only the accurate responses. Again, synonymy was observed to be costly, with a cognitive burden of increased integrative transitions between statement and model in the range of 39 to 66%.

This paper proposes a method for estimating the expected duration of competitive advantage from emerging technology adoption for the average adopting firm. The proposed method relies on publicly available data (e.g., web search interest, news articles, book titles, and firm disclosures) and integrates elements from diffusion of innovation theory, hype cycles, and resource-based view of competitive advantage. We validate this method by applying it to two mature technologies, namely ERP and cloud computing, for which we come up with estimates consistent with findings from prior studies. Leveraging our method, researchers and professionals can use readily available data to make their own estimations. Such estimates can inform researchers in answering research questions related to duration of competitive advantage from technology adoption. They can inform professionals in making better business decisions such as forecasting the net present value of an investment in an emerging technology.

This paper examines the “V-Matrix” and provides a wave theory life cycle model of organizations’ adoption of big data. The V-Matrix is based on the big data five “V’s”: Volume, Velocity, Variety, Veracity, and Value and captures and enumerates the different potential states that an organization can go through as part of its adoption and evolution towards big data. We extend the V-Matrix to a state space approach in order to provide a characterization of the adoption of big data technologies in an organization. We develop and use a wave theory of implementation to accommodate a firm’s movement through the V-Matrix. Accordingly, the V-Matrix provides a life cycle model of organizational use of the different aspects of big data. In addition, the model can help organizations’ plan for decision-making use of big data as they anticipate movement from one state to another, as they add big data capabilities. As part of this analysis, the paper examines some of the issues that occur in the different states, including synergies and other issues associated with co-occurrence of different V’s with each other. Finally, this paper integrates the V-Matrix with other data analytic life cycles and examines some of the implications of those models.

Using 86,891 tweets, from the official corporate Twitter accounts of 715 unique firms, this study examines whether and how managers strategically attract and distract investors’ attention from corporate news through Twitter. We find that firms with good earnings news use Twitter to post more earnings-related information directly, whereas firms with bad earnings news post more non-earnings-related information on Twitter. We further find that depending on earnings performance firms strategically choose the format of tweets (qualitative or quantitative) and the tone of earnings tweets (positive or negative) to attract investors’ attention to good news or distract investors’ attention from bad news. Our results are robust to difference-in-differences (DID), alternative sample periods, and different variable specifications. Our findings provide empirical evidence for investors and regulators regarding current practices in corporate information on Twitter.

Enterprise resource planning (ERP) is critical to an organization’s success. However, the factors that contribute to the success and usage of these ERP systems have received little attention. This study developed and validation of an improved DeLone-McLean IS success model. Additionally, we examined the factors which influence ERP system usage, employee satisfaction, information quality, service quality, and system quality, as well as the factors that influence the system’s overall success. The proposed model is based on a mixed-methods case study (MM-CS). The results show that the proposed model significantly measures the success of an ERP system. The organizational climate, the information quality, the system quality, and the service quality all have an impact on the usage of an ERP system. The proposed model also shows that the use of an ERP system, training and learning, and the three information (IS) quality constructs are all significant predictors of user satisfaction. The results also indicate that gender and years of ICT use on the path of ERP users have a moderating effect on the relationship between teamwork & support and use.

We propose an intermediate-term stock investment strategy based on fundamental analysis and machine learning. The approach uses predictors from the Earnings Power Index (EPI) as input variables derived from cross-sectional and time-series data from a company’s financial statements. The analytical methods of machine learning allow us to validate the link between financial factors and excess returns directly. We then select stocks for which returns are likely to increase at the time of the next disclosed financial statement. To verify the proposed approach’s usefulness, we use company data listed publicly on the Korean stock market from 2013 to 2019. We examine the profitability of trading strategy based on ten machine-learning techniques by forming long, short, and hedge portfolios with three different measures. As a result, most portfolios, including EPI-related variables, present positive returns regardless of the period. Especially, the neural network of the two layers with sigmoid function presents the best performance for the period of 3 months and 6 months, respectively. Our results show that incorporating machine learning is useful for mid-term stock investment. Further research into the possible convergence of financial statement analysis and machine-learning techniques is warranted.

Artificial Intelligence (AI) and Machine Learning (ML) are gaining increasing attention regarding their potential applications in auditing. One major challenge of their adoption in auditing is the lack of explainability of their results. As AI/ML matures, so do techniques that can enhance the interpretability of AI, a.k.a., Explainable Artificial Intelligence (XAI). This paper introduces XAI techniques to auditing practitioners and researchers. We discuss how different XAI techniques can be used to meet the requirements of audit documentation and audit evidence standards. Furthermore, we demonstrate popular XAI techniques, especially Local Interpretable Model-agnostic Explanations (LIME) and Shapley Additive exPlanations (SHAP), using an auditing task of assessing the risk of material misstatement. This paper contributes to accounting information systems research and practice by introducing XAI techniques to enhance the transparency and interpretability of AI applications applied to auditing tasks.