Do Sentiments Matter in Fraud Detection? Estimating Semantic Orientation of Annual Reports

Abstract

SUMMARYWe present a novel approach for analysing the qualitative content of annual reports. Using natural language processing techniques we determine if sentiment expressed in the text matters in fraud detection. We focus on the Management Discussion and Analysis (MD&A) section of annual reports because of the nonfactual content present in this section, unlike other components of the annual reports. We measure the sentiment expressed in the text on the dimensions of polarity, subjectivity, and intensity and investigate in depth whether truthful and fraudulent MD&As differ in terms of sentiment polarity, sentiment subjectivity and sentiment intensity. Our results show that fraudulent MD&As on average contain three times more positive sentiment and four times more negative sentiment compared with truthful MD&As. This suggests that use of both positive and negative sentiment is more pronounced in fraudulent MD&As. We further find that, compared with truthful MD&As, fraudulent MD&As contain a greater proportion of subjective content than objective content. This suggests that the use of subjectivity clues such as presence of too many adjectives and adverbs could be an indicator of fraud. Clear cases of fraud show a higher intensity of sentiment exhibited by more use of adverbs in the "adverb modifying adjective" pattern. Based on the results of this study, frequent use of intensifiers, particularly in this pattern, could be another indicator of fraud. Moreover, the dimensions of subjectivity and intensity help in accurately classifying borderline examples of MD&As (that are equal in sentiment polarity) into fraudulent and truthful categories. When taken together, these findings suggest that fraudulent MD&As in contrast to truthful MD&As contain higher sentiment content.

Text mining to detect indications of fraud in annual reports worldwide

“…Furthermore, this model included adverbs as a key feature since a greater use of adverbs indicates the presence of fraud. The ma-chine learning model of Goel and Uzuner (2016), which includes nouns, verbs, adjectives and adverbs, corroborates this result. Fraudulent 10-K reports contain more adverbs and adjectives.…”

“…Fraudulent reports contain less positive words (Tatiana Churyk et al, 2008Lee et al, 2013Lee et al, , 2014. However, Goel and Uzuner (2016) showed that the fraudulent texts contain more positive and negative emotion words. Li (2010) drew a completely different conclusion.…”

“…Goel and Uzuner (2016) took these categories into account to distinguish between fraudulent and non fraudulent MD&A sections and concluded that the categories anxiety, anger and sadness decrease the performance of their model. On the contrary, Tatiana Churyk et al (2009) and Lee et al (2014) found that fraudulent 10-K reports contain more anxiety words.…”

Big data tools for Islamic financial analysis

“…Goel and Uzuner () led a qualitative analysis of the text contained in reports for fraud detection by measuring the polarity, intensity, and subjectivity of the sentiment through management discussion and analysis. They found that a fraudulent report contains more positive and negative sentiments than a truthful report.…”

“…O'Leary (2015) underlined the importance of 'Twitter mining' by synthesizing the extant literature in using Twitter information for prediction, discovery and causation investigation. Goel and Uzuner (2016) led a qualitative analysis of the text contained in reports for fraud detection by measuring the polarity, intensity, and subjectivity of the sentiment through management discussion and analysis. They found that a fraudulent report contains more positive and negative sentiments than a truthful report.…”