1. Question difficulty evaluation has become an important research direction in the field of educational data mining, and has a lot of research work.
2. This paper comprehensively reviews the research progress of question difficulty evaluation in recent ten years, dividing it into two categories: absolute difficulty and relative difficulty.
3. The paper also summarizes related datasets and evaluation metrics of question difficulty prediction approaches, as well as provides future research directions for question difficulty evaluation.
The article is generally trustworthy and reliable, as it provides a comprehensive overview of the current state of research on question difficulty evaluation in the field of educational data mining. It divides the question difficulty into two categories - absolute difficulty and relative difficulty - and provides detailed explanations for each category. Furthermore, it also summarizes related datasets and evaluation metrics of question difficulty prediction approaches, as well as provides future research directions for question difficulty evaluation.
However, there are some potential biases that should be noted. For example, the article does not provide any evidence to support its claims about the effectiveness of deep learning based approaches for both question absolute difficulty prediction and question relative difficulty prediction. Additionally, while it mentions possible risks associated with these approaches, it does not provide any detailed information about them or how they can be mitigated. Finally, while the article does mention counterarguments to its claims, it does not explore them in detail or present both sides equally.