LASIGE, Departamento de Informática, Faculdade de Ciências, Universidade de Lisboa, Lisboa, Portugal.
CENTRA, Departamento de Física, Faculdade de Ciências, Universidade de Lisboa, Lisboa, Portugal.
Sci Data. 2022 Aug 4;9(1):478. doi: 10.1038/s41597-022-01598-7.
The recommendation of items based on the sequential past users' preferences has evolved in the last few years, mostly due to deep learning approaches, such as BERT4Rec. However, in scientific fields, recommender systems for recommending the next best item are not widely used. The main goal of this work is to improve the results for the recommendation of the next best item in scientific domains using sequence aware datasets and algorithms. In the first part of this work, we present the adaptation of a previous method (LIBRETTI) for creating sequential recommendation datasets for scientific fields. The results were assessed in Astronomy and Chemistry. In the second part of this work, we propose a new approach to improve the datasets, not the algorithms, to obtain better recommendations. The new hybrid approach is called sequential enrichment (SeEn), which consists of adding to a sequence of items the n most similar items after each original item. The results show that the enriched sequences obtained better results than the original ones. The Chemistry dataset improved by approximately seven percentage points and the Astronomy dataset by 16 percentage points for Hit Ratio and Normalized Discounted Cumulative Gain.
基于用户历史偏好的推荐物品在过去几年中得到了发展，主要得益于深度学习方法，如 BERT4Rec。然而，在科学领域，推荐下一个最佳物品的推荐系统并未得到广泛应用。本工作的主要目标是使用序列感知数据集和算法改进科学领域中推荐下一个最佳物品的结果。在本工作的第一部分，我们介绍了对以前的方法（LIBRETTI）的适应，用于为科学领域创建序列推荐数据集。结果在天文学和化学领域进行了评估。在本工作的第二部分，我们提出了一种新的方法来改进数据集，而不是算法，以获得更好的推荐。新的混合方法称为序列增强（SeEn），它由在每个原始项目之后向项目序列中添加 n 个最相似的项目组成。结果表明，与原始序列相比，增强序列获得了更好的结果。化学数据集的命中率和归一化折扣累积增益分别提高了约七个百分点，天文学数据集提高了 16 个百分点。
