Automated text mining process for corporate risk analysis and management

Governance of artificial intelligence applications in a business audit via a fusion fuzzy multiple rule-based decision-making model

“…As information technology advances, users can easily access data through the Internet. The proliferation of data size not only provides users with sufficient information, but also brings forth some challenges for users (Hu et al 2017;Zhou et al 2020;Hsu et al 2022b). For the not well-defined filed, users prefer to collect as much information as possible to comprehend the intrinsic condition.…”

“…For an unknown domain, users tend to collect as much information as possible to conjecture its real situation. However, too much information will impede/bias their decision making process and increase their cognitive burden (Li et al 2021;Hsu et al 2022b;Chang et al 2022;Kou et al 2022). To overcome this, filtering out redundant and irrelevant factors turns out to be an important pre-process.…”

Review of Survey Research in Fuzzy Approach for Text Mining

“…Hao et al developed a model that uses fuzzy logic to extract hidden topics and emotional information from online news articles in terms of features and uses fuzzy SVM to predict stock price trends, the research uses fuzzy decision boundary estimation can better predict the output and improve the credibility with compared with other methods [106], Bernabé-Moreno et al introduced a method for automatically extracting polarity dictionaries, converting vectors through TF-IDF, and evaluating news based on stock market dictionaries, analyzing the strength of each part of speech and automatically changing model weights, finally, the method is used to label news documents and compare them with stock price changes, the result found that the sentiment in the news is highly correlated with stock price changes [107], Jing et al proposed a deep learning hybrid model, by using (CNN) to analyze the sentiment in relevant posts about stocks in social software and Long-short-term memory (LSTM) to analyze the relevant indicators of the stock itself and combine the results by two-model to predict stock price [108]. Hsu et al proposed an automatic text mining method to extract subject words related to business operating risks from the descriptions in commercial financial reports, and use natural language methods to build these related words into measurement standards and evaluate the relationship between operational performance [109], Su & Chen analyzed relevant information about international manufacturers in the supply chain in Twitter and extracted words related to risks and uncertainties, the results showed that using these words to assist in the evaluation can help commercial partner selection [110], Chu et al constructed a lexicon based on past literature and utilized a thematic clustering approach to further help define potential supply chain risk factors, then the constructed dictionary is used to conduct sentiment analysis on online news articles, and the sentiment of the news is identified according to the specific risk types in the dictionary [111].…”

Peer effect, bank concentration, and crises: Evidence from the United States

“…On one hand, our findings indicate that big banks' imitation behavior leads to more non‐performing loans when the market is concentrated. Therefore, auditors and analysts should consider the potential increasing risk of big banks if they do imitate each other (e.g., Bansal, 2023; Hsu et al, 2022). On the other hand, banks themselves should possess the responsibility for maintaining financial stability.…”