Smart Book Recommender Evaluation Data

This dataset contains all the data regarding the evaluation study of the Smart Book Recommender (SBR). SBR is a semantically enhanced recommendation engine, developed in collaboration with Springer Nature (SN), for suggesting Springer books, journals and conference proceedings for conferences. SBR characterises conference in terms of their associated semantic topic covered in their proceedings and apply cosine pairwise similarity computation to find recommendations. <br>We evaluated SBR on conference series in the field of Computer Science with the help of seven SN editors and seven researchers from The Open University. The evaluation consisted of two parts: i) A quantitative analysis, which focused on analysing how evaluators rated each recommended item outputted by the SBR for two conference series of their choosing and, ii) A qualitative analysis, which focused on analysing the answers of the surveys that the evaluators completed after a hands-on session with SBR.

本数据集包含智能图书推荐系统（Smart Book Recommender，SBR）评估研究的全部相关数据。SBR是与施普林格自然（Springer Nature，SN）合作开发的语义增强型推荐引擎，用于为会议推荐施普林格旗下的图书、期刊及会议论文集。该系统依据会议论文集所涵盖的关联语义主题对会议进行特征刻画，并通过余弦成对相似度计算生成推荐结果。
本研究联合7名施普林格自然编辑与7名来自开放大学（The Open University）的研究人员，在计算机科学领域的会议系列上对SBR开展评估。本次评估包含两部分内容：一是定量分析，聚焦于评估人员针对其自选的两个会议系列，对SBR输出的每一条推荐内容的评分情况进行分析；二是定性分析，聚焦于评估人员在完成SBR实操体验后填写的调查问卷答案分析。