Recommendation based on Deduced Social Networks in an educational digital library

Discovering useful resources can be difficult in digital libraries with large content collections. Many educational digital libraries (edu-DLs) host thousands of resources. One approach to avoiding information overload involves modeling user behavior. But this often depends on user feedback, along with the demographic information found in user account profiles, in order to model and predict user interests. However, edu-DLs often host collections with open public access, allowing users to navigate through the system without needing to provide identification. With few identifiable users, building models linked to user accounts provides insufficient data to recommend useful resources. Analyzing user activity on a per-session basis, to deduce a latent user network, can take place even without user profiles or prior use history. The resulting Deduced Social Network (DSN) can be used to improve DL services. An example of a DSN is a graph whose nodes are sessions and whose edges connect two sessions that view the same resource. In this paper we present a recommendation framework for edu-DLs that depends on deduced connections between users. Results show that a recommendation system built from DSN-dependent parameters can improve performance compared to when only text similarity between resources is used. Our approach can potentially improve recommendation for DL resources when implicit user activities (e.g., view, click, search) are abundant but explicit user activities (e.g., account creation, rating, comment) are unavailable.

1. Introduction

Educational digital libraries connect content with users. The vast amount of resources and activities within an edu-DL lead to the problem of information overload - how to find useful resources in a reasonable amount of time when there is too much information to manage. The abundance of educational resources in an educational DL (edu-DL) provides opportunities but also creates problems for users when searching for high quality material. Without information on the quality of resources it becomes difficult to locate usable resources from hundreds, if not thousands, of choices. Ideally the user community provides feedback in various forms such as ratings, reviews, comments, etc. that can be helpful to gauge the quality of the resources. However, edu-DLs often host collections with public access that users can navigate through without needing to create an account and provide their feedback on the resources. Lack of user accounts poses a difficulty when building user models since these depend on attributes derived from user accounts.