Conference Agenda (All times are shown in Greenwich Mean Time (GMT) unless otherwise noted)

Research in information behavior has examined search difficulties and how people learn during searches but has not fully examined how searchers solve the difficulties on their own and gain new knowledge during this process. This study introduced the concept of insight learning during search to provide a new perspective for the studies in Search as Learning (SAL) and to optimize searchers’ experiences in a more efficient, innovative, and joyful way to combine search and learning. As a preliminary study, we conducted self-reported interviews with 30 participants to collect cases of insight learning during the search process. Based on thematic analysis of the data, we summarized the benefits of insight learning during search, described the process of how aha! occurred after impasse, and identified the antecedent, key, and consequence of insight during the search process. We aimed to help generate more insights by providing three dimensions of key factors to think about. A preliminary understanding of the insights formed in this study could contribute to further discussion about learning during the search and could help design new search tools that support effective learning.

In this concept paper, we make the case that variables related to reading and comprehension are relevant to the design of searching as learning environments. We propose that measures of cohesion – the lexical and grammatical connectedness within and between texts – be used as signals in retrieval and ranking algorithms for such environments, as cohesion is an important factor in text comprehension and learning. In illustrating this concept, we introduce a use case for learning-oriented search in which the task is to retrieve a multi-document set that functions as a spontaneous learning environment. For this task, features of the document set as a whole are important in addition to features of individual documents. In this paper we focus on the goals of achieving a mid-range level of readability and cohesion across a set of texts in order to balance comprehensibility with challenge and stimulation.

This study evaluates the effectiveness of various readability measures when assessing the difficulty of film materials for English Language Learners (ELLs). Library materials catering to ELLs are frequently limited to formal instruction texts and fiction materials. This study explores the feasibility of less laborious, computational text assessment methods to better understand library holdings from the perspective of ELL appropriateness. The investigation applies traditional formulaic readability measures and modern cohesion methods to film subtitle data. While text difficulty assessment with readability measures has been widely studied, there is a need to investigate which measures are most suitable for film application. In addition to evaluating existing readability measures, a more robust composite score is also presented, combining aspects of traditional readability formulas and modern cohesion methods. The experiments were conducted on real-world datasets and tested on film data marked for difficulty by ELLs.

User search performance is multidimensional in nature and may be better characterized by metrics that depict users' interactions with both relevant and irrelevant results. Despite previous research on one-dimensional measures, it is still unclear how to characterize different dimensions of user performance and leverage the knowledge in developing proactive recommendations. To address this gap, we propose and empirically test a framework of search performance evaluation and build early performance prediction models to simulate proactive search path recommendations. Experimental results from four datasets of diverse types (1,482 sessions and 5,140 query segments from both controlled lab and natural settings) demonstrate that: 1) Cluster patterns characterized by cost-gain-based multifaceted metrics can effectively differentiate high-performing users from other searchers, which form the empirical basis for proactive recommendations; 2) whole-session performance can be reliably predicted at early stages of sessions (e.g., first and second queries); 3) recommendations built upon the search paths of system-identified high-performing searchers can significantly improve the search performance of struggling users. Experimental results demonstrate the potential of our approach for leveraging collective wisdom from automatically identified high-performance user groups in developing and evaluating proactive in-situ search recommendations.