1) 将Embedding model分别用在Sequential POI data和real comment (content) of POI上，然后用超级参数sum在一起。
2）概率模型，通过极大似然sum之后的objective function，求参数
3）提供了带有评论的POI数据
| 文献题目 | 去谷歌学术搜索 | ||||||||||
| Content-Aware Hierarchical Point-of-Interest Embedding Model for Successive POI Recommendation | |||||||||||
| 文献作者 | Buru Chang | ||||||||||
| 文献发表年限 | 2018 | ||||||||||
| 文献关键字 | |||||||||||
| Embedding model, Sequential information + content of POI | |||||||||||
| 摘要描述 | |||||||||||
| Recommending a point-of-interest (POI) a user will visit next based on temporal and spatial context information is an important task in mobile-based applications. Recently, several POI recommenda- tion models based on conventional sequential-data modeling approaches have been proposed. How- ever, such models focus on only a user’s check- in sequence information and the physical distance between POIs. Furthermore, they do not utilize the characteristics of POIs or the relationships be- tween POIs. To address this problem, we pro- pose CAPE, the first content-aware POI embedding model which utilizes text content that provides in- formation about the characteristics of a POI. CAPE consists of a check-in context layer and a text con- tent layer. The check-in context layer captures the geographical influence of POIs from the check-in sequence of a user, while the text content layer cap- tures the characteristics of POIs from the text con- tent. To validate the efficacy of CAPE, we con- structed a large-scale POI dataset. In the experi- mental evaluation, we show that the performance of the existing POI recommendation models can be significantly improved by simply applying CAPE to the models. | |||||||||||
