• Publications
  • Influence
DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis
Two deep-learning systems that competed at SemEval-2017 Task 4 “Sentiment Analysis in Twitter” are presented, which use Long Short-Term Memory networks augmented with two kinds of attention mechanisms, on top of word embeddings pre-trained on a big collection of Twitter messages. Expand
Semantic trajectories modeling and analysis
A survey of the approaches and techniques for constructing trajectories from movement tracks, enriching trajectories with semantic information to enable the desired interpretations of movements, and using data mining to analyze semantic trajectories to extract knowledge about their characteristics. Expand
Algorithms for Nearest Neighbor Search on Moving Object Trajectories
Nearest Neighbor (NN) search has been in the core of spatial and spatiotemporal database research during the last decade. The literature on NN query processing algorithms so far deals with eitherExpand
Nearest Neighbor Search on Moving Object Trajectories
Mechanisms to perform NN search on R-tree-like structures storing historical information about moving object trajectories, including the TB-tree, are investigated and their scalability and efficiency are demonstrated through an extensive experimental study using synthetic and real datasets. Expand
Basic Concepts of Movement Data
Building real-world trajectory warehouses
This work investigates how the traditional data cube model is adapted to trajectory warehouses in order to transform raw location data into valuable information. Expand
Literature review of spatio-temporal database models
This paper reviews the different types of spatio-temporal data models that have been proposed in the literature as well as new theories and concepts that have emerged and critically evaluates the various approaches through the use of a case study and the construction of a comparison framework. Expand
Similarity Search in Trajectory Databases
This paper introduces a framework consisting of a set of distance operators based on primitive as well as derived parameters of trajectories (speed and direction) to support trajectory clustering and classification mining tasks, which definitely imply a way to quantify the distance between two trajectories. Expand
Hermes - A Framework for Location-Based Data Management
The aim of this paper is to demonstrate Hermes, a robust framework capable of aiding a spatio-temporal database developer in modeling, constructing and querying a database with dynamic objects thatExpand
Path-based queries on trajectory data
An extensive performance study of NETTRA using a very large real-world trajectory data set, consisting of 1.7 million trajectories and a road network with 1.3 million edges, shows a speed-up of two orders of magnitude compared to state-of-the-art trajectory indexes. Expand