Abstract: [Purpose/Significance] This paper aims to study the structure-utility relationship of descriptive information of scientific data to provide a new perspective for the theoretical study of scientific data description and a reference for the best description of agricultural scientific data in the digital environment. [Method/Process] Based on information processing theory, the lens model, the probabilistic mental model theory and the adaptive decision-making behavior framework, the relationship model between descriptive information structure and informing utility was constructed. A situational experiment was designed according to the model. In this study, 47 postgraduates from 14 institutes were invited for quasi-experimental observation by using qualitative and quantitative methods such as eye-tracking, semi-structured interview and questionnaire. First, this study used a semi-structured interview to obtain a user's cognitive interpretation of fixation points and collected the descriptive items of agricultural scientific data and their use frequency by encoding the interview text. Second, this study combined descriptive item usage path coding and user judgment confidence to obtain the combination of descriptive items with high utility. Finally, the study used multiple regression analysis to identify the descriptive items with high utility and their predictive ability, and analyzed the impact of data literacy and data utilization type on the utility of descriptive items. [Results/Conclusions] The study identified 42 descriptive items of 11 categories of agricultural scientific data and their usage characteristics. Among them, the top 5 frequently used descriptive items were subject, data, overall description, source and data production information, which played an important role in user relevance judgment. Then this study identified the combination of descriptive items with high utility and found that users' use patterns of descriptive items were diverse. Compared with making a judgment with "relevant" result, users often needed less information to achieve a high level of confidence when making an "irrelevant" judgment. This study also found that the descriptive items with high utility include source, data, use and evaluation, and data production information. It is determined that user data literacy and data utilization purpose were the influencing factors of descriptive information utility, and the effects of the two factors were preliminarily analyzed. Based on this research, the paper put forward some suggestions for improving agricultural scientific data metadata and scientific data sharing. In the future, this study will be repeated in groups with different academic backgrounds and data literacy levels, so as to enhance the generalization ability of research conclusions and construct a more effective structure of scientific data descriptive information.

Key words: scientific data, data description, metadata, information utility, eye-tracking