Figure 4
The thematic map is drawn on a coordinate plane divided into four quadrants by a vertical and a horizontal dashed line. The horizontal axis is labeled “Relevance degree (Centrality)” and runs from low on the left to high on the right. The vertical axis is labeled “Development degree (Density)” and runs from low at the bottom to high at the top. The four quadrants are implicitly labeled as upper left niche themes, upper right motor themes, lower left emerging or declining themes, and lower right basic themes. In the upper right quadrant, a green circular cluster contA Ins the keywords “neural network”, “logistic regression”, and “bankruptcy”. Slightly to the left within the upper central area, a red circular cluster contA Ins “machine learning”, “fraud detection”, and “deep learning”. In the central region near the intersection of the dashed lines, a purple circular cluster contA Ins “data mining”, “natural language processing”, and “classification”. In the upper left quadrant, a small orange cluster contA Ins “big data”, “data analytics”, and “management accounting”. In the lower left quadrant, another small orange cluster contA Ins “artificial neural networks”, “earnings management”, and “prediction”. In the lower right quadrant, a large blue circular cluster contA Ins “artificial intelligence”, “auditing”, and “accounting”.Thematic map. Source: The Authors