关键词: 交互式数据探索, 主题提取, 特征选择, 样本发现, 机器学习

Abstract: Interactive data exploration(IDE)is a key technique in a diverse set of discovery-based applications， which focuses on interaction， exploration and discovery and has a wide range of applications in many scenes and areas. The feature adaptive technology of interactive data exploration was studied in this paper with the background of massive academic literature data exploration. Firstly， a framework of interactive data exploration was presented， namely FA-IDE(feature-adaptive interactive data exploration) framework， which can dynamically adjust the subset of features during each iteration to meet the needs of the user′s interest diversity. Secondly， according to this framework， the evaluation criteria of the balance of feature subsets(BFS) were proposed in the stage of exploration and a sequence forward feature selection algorithm based on BFS was also given. Besides， for the phases of related sample discovery， a division level establishment method was proposed. According to the decision tree model which can divide the user interest area， a strategy of result set sorting based on similarity was proposed.The results of experiments show that the accuracy and efficiency of the proposed method have been effectively improved.

Key words: interactive data exploration, topic extraction, feature selection, sample discovery, machine learning