Abstract

Internet, and particularly the World Wide Web (WWW), has become the main resource for students who look for information to complete their school assignments. Although abundant, not all the content on the Web is curated[1]. This poses a major problem for students who may not be well equipped in terms of OIC. Indeed, knowing what information is needed and how to search for it (i.e., some component skills of OIC) is crucial to succeed in online research [2]. To tackle this problem, different approaches to help students in the development of OIC have been proposed [1, 3]. A fundamental limitation of these approaches is their inability to timely determine whether students will succeed or fail when engaging in actual search tasks. In the context of OIC development, knowing in advance how a student will perform in a search task could be particularly useful to both educators and students. First, educators could offer opportune feedback and support to their students, thus avoiding late evaluations typically available only after tests are completed. Second, students themselves could be more aware of their own performance, which could help them to correct themselves or look for support. In educational contexts, prediction focuses on forecasting performance by estimating unknown values of variables that characterize students. Such values typically relate to performance, knowledge, and scores. Prediction can be also used to: identify learning styles, determine whether a student will answer a question correctly, model knowledge changes, and determine non-observable learning variables [4]. In this article, we explore the possibility to anticipate student’s search performance by exploiting a set of demographic, behavioral, cognitive, and affective features through machine learning. The remaining sections of this article are organized as follows. First, we describe the methodological approach adopted for this work. Second, we present preliminary results. Finally, we conclude with a discussion of the results, their implications, and future work.