Recently, searching for information by using search engines such as Google, Bing, and NAVER has become ubiquitous. While they attempt to provide information based on the search queries that users enter, it is not trivial to accurately capture the search intent of users. Motivated by this situation, NAVER Corp., the largest portal company in Korea, has developed a framework named as CATER (Cluster-based Alternative TErm Recommendation) framework that suggests alternative terms ("al-terms,'' in short) for better search outcomes relevant to a user's search intent. We introduce four design considerations (DCs) that were considered when designing and implementing CATER. Then, we describe how our CATER addresses the four DCs by using a clustering stage that dynamically maintains a pool of topic-oriented clusters containing terms, and a recommendation stage that identifies the top-k clusters (i.e., topics) and the top-k al-terms for each cluster. Furthermore, we present the scalable architecture adopted by CATER. Through various offline and online A/B tests using real-world datasets from NAVER, we validate that CATER successfully incorporates all DCs and that all design choices help improve the recommendation accuracy.

The goal of Review-Based Recommendation System (RBRS) is to effectively learn the representations of users and items by utilizing review texts in addition to user-item interactions. From user-item interaction graphs widely employed in recommendation systems, recent RBRS methods using graph neural networks (GNNs) obtain the representations by associating each edge between a user and an item with the review information of the user for that item. However, these GNN-based RBRS methods present two main issues: (1) by con- verting each review text into the weight, i.e., single value, of a edge between a user node and an item node, they lose the rich informa- tion about users and items inherent in the review; and (2) by creating only a single general representation for each user, they cannot repre- sent the individual effects of users' likes and dislikes on their ratings for items they have interacted with. To address these problems, we propose a novel GNN-based RBRS, named LETTER, utilizing homo- geneous graphs, i.e., user-user graphs and an item-item graph, to learn general representations of users and items along with users' like and dislike representations. LETTER can learn user and item representations without losing review information by utilizing the proposed homogeneous graphs. Furthermore, LETTER explicitly designs the influence of users' like and dislike representations on their ratings to perform accurate rating predictions. Through ex- periments on six datasets, we verify that the proposed LETTER out- performs nine state-of-the-art RBRSs by up to 23.1%. Our source code is available at https://github.com/Bigdasgit/LETTER.

Traffic speed prediction is a crucial task for optimizing navigation systems and reducing traffic congestion. Although there have been efforts to improve the accuracy of speed prediction by incorporating auxiliary features, such as traffic flow, weather, and time, types of auxiliary features are limited and their detailed relationships with speed have not been explored yet. In our study, we present the individual spatio-temporal (IST) dependencies on flow and speed, and characterize three types of IST-dependencies with the flow-to-flow, speed-to-speed, and flow-to-speed graphs. Then, we propose Auxiliary feature-aided Attention Network (ARIAN), a novel approach to judiciously learning the degrees of IST-dependencies with the three graphs and predicting the future speed by leveraging various auxiliary features. Through comprehensive experiments using 3 real-world datasets, we validate the superiority of ARIAN over 10 state-of-the-art methods and the effectiveness of each auxiliary feature and each dependency learner in ARIAN.

Spatio-temporal models, which combine GNNs (Graph Neural Networks) and RNNs (Recurrent Neural Networks), have shown state-of-the-art accuracy in traffic speed prediction. However, we find that they consider the spatial and temporal dependencies between speeds separately in the two (i.e., space and time) dimensions, thereby unable to exploit the joint-dependencies of speeds in space and time. In this paper, with the evidence via preliminary analysis, we point out the importance of considering individual dependencies between two speeds from all possible points in space and time for accurate traffic speed prediction. Then, we propose an Individual Spatio-Temporal graph (IST-graph) that represents the Individual Spatio-Temporal dependencies (IST-dependencies) very effectively and a Spatio-Temporal Graph ATtention network (ST-GAT), a novel model to predict the future traffic speeds based on the IST-graph and the attention mechanism. The results from our extensive evaluation with five real-world datasets demonstrate (1) the effectiveness of the IST-graph in modeling traffic speed data, (2) the superiority of ST-GAT over 5 state-of-the-art models (i.e., 2-33% gains) in prediction accuracy, and (3) the robustness of our ST-GAT even in abnormal traffic situations.