The latent friend recommendation in online social media is interesting, yet challenging, because the user-item ratings and the user–user relationships are both sparse. In this paper, we propose a new dual implicit mining-based latent friend recommendation model that simultaneously considers the implicit interest topics of users and the implicit link relationships between the users in the local topic cliques. Specifically, we first propose an algorithm called all reviews from a user and all tags from their corresponding items to learn the implicit interest topics of the users and their corresponding topic weights, then compute the user interest topic similarity using a symmetric Jensen–Shannon divergence. After that, we adopt the proposed weighted local random walk with restart algorithm to analyze the implicit link relationships between the users in the local topic cliques and calculate the weighted link relationship similarity between the users. Combining the user interest topic similarity with the weighted link relationship similarity in a unified way, we get the final latent friend recommendation list. The experiments on real-world datasets demonstrate that the proposed method outperforms the state-of-the-art latent friend recommendation methods under four different types of evaluation metrics.

中文翻译：

---

基于双重隐式挖掘的潜在好友推荐

在线社交媒体中的潜在好友推荐很有趣，但也很有挑战性，因为用户-项目评分和用户-用户关系都很稀疏。在本文中，我们提出了一种新的基于双重隐式挖掘的潜在朋友推荐模型，该模型同时考虑了用户的隐式兴趣主题和本地主题团中用户之间的隐式链接关系。具体来说，我们首先提出了一种算法，称为来自用户的所有评论和来自其相应项目的所有标签，以学习用户的隐含兴趣主题及其相应的主题权重，然后使用对称 Jensen-Shannon 散度计算用户兴趣主题相似度。之后，我们采用所提出的带重启算法的加权局部随机游走来分析局部主题团中用户之间的隐式链接关系，并计算用户之间的加权链接关系相似度。将用户兴趣话题相似度与加权链接​​关系相似度统一结合，得到最终的潜在好友推荐列表。在真实世界数据集上的实验表明，在四种不同类型的评估指标下，所提出的方法优于最先进的潜在朋友推荐方法。