1. Querying and Exploring Geospatial Data  

• Survey: Location- and Keyword-based querying of geo-textual data  (VLDB Journal, 2021)

            We would like to update the survery regularly, and if we miss your work on the topic, please drop us an email.

• Survey: A Survey on Trajectory Data Management, Analytics, and Learning (ACM Comput. Surv., 2021)

1.1 Querying spatio-textual (geo-textual) data streams

Selected publications:

• SSTD: A Distributed System on Streaming Spatio-Textual Data, PVLDB 2020
• STAR: A Distributed Stream Warehouse System for Spatial Data. SIGMOD Conference 2020: 2761-2764 (Demo)
• Distributed Publish/Subscribe Query Processing on the Spatio-Textual Data Stream (ICDE 17)
• Diversity-aware top-k publish/subscribe on text stream (SIGMOD 15)
• Temporal spatial-keyword top-k publish/subscribe on geo-textual data stream (ICDE15 and demo in VLDB14)
• Boolean spatial-keyword publish/subscribe on geo-textual data stream (SIGMOD13  and demo in VLDB14)

1.2 Data exploration for spatial data: Region search & topic exploration

Selected publications:

• SURGE: Continuous Detection of Bursty Regions Over a Stream of Spatial Objects (TKDE19, ICDE18)
• Finding attribute-aware similar regions for data analysis (PVLDB 19)
• Efficient Similar Region Search with Deep Metric Learning (KDD 18)
• Efficient Selection of Geospatial Data on maps for Interactive Visualized Exploration (SIGMOD 18)
• Towards Best Region Search for Data Exploration (SIGMOD 2016)
• Topic Exploration in Spatio-Temporal Document Collections(SIGMOD 2016, VLDBJ19)

1.2 Spatial keyword queries

• On Spatial Pattern Matching (ICDE’17, VLDBJ’19)
• Answering the m-closest keywords query (SIGMOD 15)
• Search regions of interest for user exploration  (VLDB14)
• Distributed spatial keyword querying on road networks (EDBT14)
• An evaluation of 12 geo-spatial indexes (VLDB13). Code available here. 
• An overview paper on spatial-keyword querying (invited paper in ER)
• Route planning: answering queries like “a most popular route such that it passes by shopping malls, restaurant, and pub, and the travel time is within 4 hours.” (PVLDB12)
• Efficient processing of several types of spatial keyword queries (VLDB09, PVLDB10, SIGMOD11a).  Code for our SIGMOD11 paper is available here.  An extension of our SIGMOD 11 paper is published in TODS
• Efficient algorithms and cost models for reverse spatial-keyword k-nearest neighbor search (SIGMOD11b, TODS14)
• Efficient spatial keyword search in trajectory databases (unpublished paper)

2. Spatial Data Mining and Spatial-temporal Data Mining

2.1 Road network representation

• Robust Road Network Representation Learning: When Traffic Patterns Meet Traveling Semantics, CIKM2021

2.2 Intelligent transportation using trajectory data

Selected Publications:

• Trajectory simplification: ICDE 2021, KDD 2021
• Online Anomalous Trajectory Detection with Deep Generative Sequence Modeling, ICDE2020
• Spatial Transition Learning on Road Networks with Deep Probabilistic Models, ICDE 2020
• Learning Travel Time Distributions with Deep Generative Model. (WWW 2019)

2.3 Data driven smart city applications

• Periodic-CRN: A Convolutional Recurrent Model for Crowd Density Prediction with Recurring Periodic Patterns (IJCAI, 2018)
• Efficient Similar Region Search with Deep Metric Learning (KDD 2018)

2.4 Spatial graph mining,  POI recommendation & prediction

• Densely Connected User Community and Location Cluster Search in Location-Based Social Networks, SIGMOD2020
• Context-aware Deep Model for Joint Mobility and Time Prediction, WSDM 2020
• More work on POI recommendation in Project 4

3. Machine Learning for Data Management

3.1 Deep learning for databases

• Cardinality and selectivity estimation:  A Unified Deep Model of Learning from both Data and Queries for Cardinality Estimation, SIGMOD'21
• Workload generation
• Indexing optimization:  The RLR-Tree: A Reinforcement Learning Based R-Tree for Spatial Data

3.2 Deep learning for trajectory similarity and search

Selected Publications:

• Efficient and Effective Similar Subtrajectory Search with Deep Reinforcement Learning, PVLDB 2020 
• Deep Learning for Trajectory Similarity Search (ICDE18, ICDE19)
• Effective and Efficient Sports Play Retrieval with Deep Representation Learning (KDD19)

4. Recommendation, POI recommendation and User Behaviour Modeling

4.1 Recommendation and group recommendation

Selected publications:

• HyperML: A Boosting Metric Learning Approach in Hyperbolic Space for Recommender Systems. WSDM 2020 (Best paper award runner-up)
• Global Context Enhanced Graph Nerual Networks for Session-based Recommendation, SIGIR 2020
• Interact and Decide: Medley of Sub-Attention Networks for Effective Group Recommendation (SIGIR 19)
• Group Recommendation based on topic models(KDD14)    

4.2 POI recommendation

• HME: A Hyperbolic Metric Embedding Approach for Next-POI Recommendation, SIGIR 2020
• A new POI recommentdation approach, which performs better than previous approaches in experiments (SIGIR 2015)
• SAR: A sentiment-aspect-region model for user preference analysis and POI/user recommendation. The model provides explanations for recommendation results.  (ICDE 2015)
• A general graph model for recommendation in heterogeneous networks and its applications in event-based social networks (ICDE 2015)
• Diversity-aware POI recommendation (AAAI 2015)
• Time-aware POI recommendation (SIGIR13, CIKM14).  Datasets available here
• Mining significant semantic locations from user generated GPS data for recommendation (PVLDB10)

4.3 User behaviour modeling

• W4: Discovering spatio-temporal topics for individual users and its various applications, e.g., requirement-aware POI recommendation  (KDD13, TOIS15).   Datasets available here

5. Mining Reviews, Social Media, and Forums

• We consider the impact of users' attributes,  time factor, and novelty decay (Repeated exposures of an individual to an idea may have diminishing influence on the individual) for finding influential users.
• We develop techniques for review mining and sentiment analysis. 
• We also develop techniques for mining social media, including Micro-blogs (e.g., Twitter), and Community Based Question Answering Sites (e.g., Yahoo! Q&A).

Publications:

• Inf2vec: Latent Representation Model for Social Influence Embedding (ICDE 18)
• DynaDiffuse: A dynamic diffusion model for continuous time constrained influence maximization (AAAI 15)
• Finding influential event organizers in event based social networks (SIGMOD14)
• Influence maximization with novelty decay (AAAI14)
• Time constrained influence maximization in social networks ( ICDM12 , TKDE . Source code)
• Computing top-k influential nodes (KDD10, AAAI 11)  
• Detecting user intents from tweets (AAAI 15)
• Coarse-to-fine review selection via supervised joint aspect and sentiment model (SIGIR14)
• One seed to find them all: Mining opinion features via association (CIKM12)
• Geolocation prediction for social images by exploring user profiles (JASIST14) 
• On predicting popularity of newly emerging hashtags in Twitter (JASIST13)
• Short text classification ( WWW12 poster, evaluation paper JASIST ) and hierarchy maintenance ( SIGIR12).  Annotated dataset  for our SIGIR12 paper is available here.
• Using categorization information to improve question search in community based question answering services ( CIKM09, WWW2010, TOIS12). Annotated dataset is available here
• Extracting Question-Answer pairs from forums to build the QA database (SIGIR08, ACL08)
• Routing questions to expert users ( ICDE09)

Acknowledgement: Some of these projects are supported by grants awarded by Ministry of Education, NRF, IAF, Singtel/NCS, Roll-Royce, and Microsoft.