Point-of-Interest (POI) search is vital for location-based services, aiding users in finding relevant locations. While general textual semantic matching and spatial keyword queries have been well-studied, personalized POI search has received less attention. Analyzing real-world POI search data reveals that user preferences for geographical distances and regions vary and are dynamic, highlighting the need for query-dependent personalization. To address this, we introduce the QPL (Query-dependent user Preference on geographical factors Learning) model. This model simultaneously addresses textual relevance and user preference learning. It features a novel textual matching module that combines traditional lexical matching with deep semantic relevance, and a user preference learning module that adapts to query-dependent preferences for distance and region. A Cross Attention Layer further captures the relationship between query and POI regions. Extensive experiments on two real-world datasets demonstrate our model's effectiveness. The source code is available at https://github.com/Shawn-hub-hit/QPL-master

In this work, we propose a Unified framework of Sequential Search and Recommendation (UnifiedSSR) for joint learning of user behavior history in both search and recommendation scenarios. Specifically, we consider user-interacted products in the recommendation scenario, as well as user-interacted products and user-issued queries in the search scenario as three distinct types of user behaviors. We propose a dual-branch network to encode the pair of interacted product history and issued query history in the search scenario in parallel. This allows for cross-scenario modeling by deactivating the query branch for the recommendation scenario. Through the parameter sharing between dual branches, as well as between product branches in two scenarios, we incorporate cross-view and cross-scenario associations of user behaviors, providing a comprehensive understanding of user behavior patterns. To further enhance user behavior modeling by capturing the underlying dynamic intent, an Intent-oriented Session Modeling module is designed for inferring intent-oriented semantic sessions from the contextual information in behavior sequences. In particular, we consider self-supervised learning signals from two perspectives for intent-oriented semantic session locating, which encourage session discrimination within each behavior sequence and session alignment between dual behavior sequences. Extensive experiments on three public datasets demonstrate that UnifiedSSR consistently outperforms state-of-the-art methods for both search and recommendation.

Geo-textual objects with both geographical location and textual description are gaining in prevalence. Over the past decades, substantial research has been conducted on spatial keyword queries, which integrate location into keyword-based querying of geo-textual content. However, existing proposals mostly focus on efficiency for processing spatial keyword queries, and little effort was made to address the effectiveness perspectives. In this work, using two datasets with ground truth query results, we evaluate the effectiveness of standard spatial keyword queries. Our evaluation results show that the TkQ query that ranks objects by a weighted combination of spatial proximity and text relevance is the most effective. Motivated by the finding, we propose a Deep relevance with Weight learning (DrW) model to further improve the effectiveness of the retrieval ranking. DrW is featured with two novel ideas: First, we propose a neural network architecture to learn the text relevance matching over the local interaction between the query and geo-textual objects. Second, we find that a query-dependent weight to balance text relevance and spatial proximity in ranking can improve effectiveness, and we develop a learning-based method to learn the query-dependent weight. Experimental results reveal that our model outperforms state-of-the-art methods on effectiveness, with improvements up to 32.15%, 32.34%, and 33.00% in terms of NDCG@3, NDCG@5, and MRR.

As a fundamental component in location-based services, inferring the relationship between points-of-interests (POIs) is very critical for service providers to offer good user experience to business owners and customers. Most of the existing methods for relationship inference are not targeted at POI, thus failing to capture unique spatial characteristics that have huge effects on POI relationships. In this work we propose PRIM to tackle POI relationship inference for multiple relation types. PRIM features four novel components, including a weighted relational graph neural network, category taxonomy integration, a self-attentive spatial context extractor, and a distance-specific scoring function. Extensive experiments on two real-world datasets show that PRIM achieves the best results compared to state-of-the-art baselines and it is robust against data sparsity and is applicable to unseen cases in practice.

To provide more accurate personalized product search (PPS) results, it is compulsory to go beyond modeling user-query-item interaction. Graph embedding techniques open the potential to integrate node information and topological structure information. Existing graph embedding enhanced PPS methods are mostly based on entity-relation-entity graph learning. In this work, we propose to consider structural relationship in users' product search scenario with graph embedding by latent representation learning. We argue that explicitly modeling the structural relationship in graph embedding is essential for more accurate PPS results. We propose a novel method, Graph embedding based Structural Relationship Representation Learning (GraphSRRL), which explicitly models the structural relationship in users-queries-products interaction. It combines three key conjunctive graph patterns to learn graph embedding for better PPS. In addition, GraphSRRL facilitates the learning of affinities between users (resp. queries or products) in the designed geometric operation in low-dimensional latent space. We conduct extensive experiments on four datasets to evaluate GraphSRRL for PPS. Experimental results show that GraphSRRL outperforms the state-of-the-art algorithm on real-world search datasets by at least 50.7% in term of [email protected] and 48.7% in terms of [email protected]

With the increasing popularity of micro-video sharing where people shoot short-videos effortlessly and share their daily stories on social media platforms, the micro-video recommendation has attracted extensive research efforts to provide users with micro-videos that interest them. In this paper, a hypothesis we explore is that, not only do users have multi-modal interest, but micro-videos have multi-modal targeted audience segments. As a result, we propose a novel framework User-Video Co-Attention Network (UVCAN), which can learn multi-modal information from both user and microvideo side using attention mechanism. In addition, UVCAN reasons about the attention in a stacked attention network fashion for both user and micro-video. Extensive experiments on two datasets collected from Toffee present superior results of our proposed UVCAN over the state-of-the-art recommendation methods, which demonstrate the effectiveness of the proposed framework.