Cluster-based text mining for extracting drug candidates for the prevention of COVID-19 from the biomedical literature.

Objective: The coronavirus disease 2019 (COVID-19) health crisis that began at the end of 2019 made researchers around the world quickly race to find effective solutions. Related literature exploded and it was inevitable that an automated approach was needed to find useful information, namely text mining, to overcome COVID-19, especially in terms of drug candidate discovery. While text mining methods for finding drug candidates mostly try to extract bioentity associations from PubMed, very few of them mine with a clustering approach. The purpose of this study was to demonstrate the effectiveness of our approach to identify drugs for the prevention of COVID-19 through literature review, cluster analysis, drug docking calculations, and clinical trial data. Methods: This research was conducted in four main stages. First, the text mining stage was carried out by involving Bidirectional Encoder Representations from Transformers for Biomedical to obtain vector representation of each word in the sentence from texts. The next stage generated the disease-drug associations, which were obtained from the correlation between disease and drug. Next, the clustering stage grouped the rules through the similarity of diseases by utilizing Term Frequency-Inverse Document Frequency as its feature. Finally, the drug candidate extraction stage was processed through leveraging PubChem and DrugBank databases. We further used the drug docking package AUTODOCK VINA in PyRx software to verify the results. Results: Comparative analyses showed that the percentage of findings using mining with clustering outperformed mining without clustering in all experimental settings. In addition, we suggest that the top three drugs/phytochemicals by drug docking analysis may be effective in preventing COVID-19. Conclusions: The proposed method for text mining utilizing the clustering method is quite promising in the discovery of drug candidates for the prevention of COVID-19 through the biomedical literature.

Model-based analysis of thinking in problem posing as sentence integration focused on violation of the constraints.

The advancement of computer and communication technologies has enabled researchers to conduct and analyze the learning process of posing problems. This study investigates what learners think while posing problems as sentence integration in terms of intermediate products as well as the posed problems as the resultant product. Problem posing as sentence integration defines the arithmetic word problem structure, and posing a problem is a task to satisfy all the constraints and requirements to build a valid structure. A previous study shows that, in problem posing as sentence integration for arithmetic word problems, learners try to satisfy a relatively large number of constraints in the posed problems. In contrast, this study focuses on the violation of constraints in the intermediate products while posing problems. The result shows that learners were inclined to avoid as many violated constraints as possible throughout the problem-posing process. Although learners tend to avoid the violated constraints, naturally, they cannot avoid some mistakes. Further analysis shows that learners actually have difficulty in fulfilling particular constraints while posing the problems. Based on this analysis, it is possible to detect the difficulty of learners' actions from the model perspective. Hence, it is possible to give accurate feedback and appropriately support the learners.

Visualizations of problem-posing activity sequences toward modeling the thinking process.

Problem-posing is well known as an effective activity to learn problem-solving methods. Although the activity is considered in contributing to the understanding of the problem's structure, it is not clear how learners could understand it through the activity. This study proposes a method to offer a visual representation for analyzing the problem-posing activity sequence in MONSAKUN, a digital learning environment for problem-posing of arithmetic word problems via sentence integration. This system requires users to pose a problem through combinations of given simple sentences based on the requirement. The system writes every single action into logs as sequences of problem-posing activity. The sequences are considered to represent the thinking processes of learners. The thinking process reflects their understanding and misunderstanding about the structure of the problems. This study created visualizations of learners' problem-posing processes from the data obtained through the practical use of MONSAKUN, including the states in which many learners had difficulties finding the correct answer. In this study, we refer to such states as "trap states." In MONSAKUN, a trap state is a combination of simple sentences where many learners tend to make and need relatively more actions to obtain the correct answer. As the result of the visualization and analysis of the data, some trap states have been identified, and they changed for each trial in the same problem.