Gianni Barlacchi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Gianni Barlacchi has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Bruno Lepri
Fondazione Bruno Kessler, Trento, Italy
6 shared publications - Alberto Rossi
University of Florence
2 shared publications Alessandro Moschitti
Department of Information Engineering and Computer Science, University of Trento, Trento, Italy
2 shared publicationsBruno Lepri
Bruno Kessler Foundation (FBK)
2 shared publications- Luca Pappalardo
Institute of Information Science and Technologies (ISTI), National Research Council (CNR), Pisa, Italy
2 shared publications - Massimiliano Luca
Mobile and Social Computing Lab, Fondazione Bruno Kessler, Trento, Italy
2 shared publications
Latest Publications
- 6 September 2023
- Published by Springer Nature in Machine Learning
- Vol. 112 (11) , 4597-4634
Trajectory test-train overlap in next-location prediction datasets
- 6 September 2023
- Published by Springer Nature in Machine Learning
- Vol. 112 (11) , 4597-4634
Trajectory test-train overlap in next-location prediction datasets
- Open Access
From Rewriting to Remembering: Common Ground for Conversational QA Models
In conversational QA, models have to leverage information in previous turns to answer upcoming questions. Current approaches, such as Question Rewriting, struggle to extract relevant information as the conversation unwinds. We introduce the Common Ground (CG), an approach to accumulate conversational information as it emerges and select the relevant information at every turn. We show that CG offers a more efficient and human-like way to exploit conversational information compared to existing approaches, leading to improvements on Open Domain Conversational QA.
Open AccessFrom Rewriting to Remembering: Common Ground for Conversational QA Models
In conversational QA, models have to leverage information in previous turns to answer upcoming questions. Current approaches, such as Question Rewriting, struggle to extract relevant information as the conversation unwinds. We introduce the Common Ground (CG), an approach to accumulate conversational information as it emerges and select the relevant information at every turn. We show that CG offers a more efficient and human-like way to exploit conversational information compared to existing approaches, leading to improvements on Open Domain Conversational QA.
- Open Access
Trajectory Test-Train Overlap in Next-Location Prediction Datasets
Next-location prediction, consisting of forecasting a user's location given their historical trajectories, has important implications in several fields, such as urban planning, geo-marketing, and disease spreading. Several predictors have been proposed in the last few years to address it, including last-generation ones based on deep learning. This paper tests the generalization capability of these predictors on public mobility datasets, stratifying the datasets by whether the trajectories in the test set also appear fully or partially in the training set. We consistently discover a severe problem of trajectory overlapping in all analyzed datasets, highlighting that predictors memorize trajectories while having limited generalization capacities. We thus propose a methodology to rerank the outputs of the next-location predictors based on spatial mobility patterns. With these techniques, we significantly improve the predictors' generalization capability, with a relative improvement on the accuracy up to 96.15% on the trajectories that cannot be memorized (i.e., low overlap with the training set).
Open AccessTrajectory Test-Train Overlap in Next-Location Prediction Datasets
Next-location prediction, consisting of forecasting a user's location given their historical trajectories, has important implications in several fields, such as urban planning, geo-marketing, and disease spreading. Several predictors have been proposed in the last few years to address it, including last-generation ones based on deep learning. This paper tests the generalization capability of these predictors on public mobility datasets, stratifying the datasets by whether the trajectories in the test set also appear fully or partially in the training set. We consistently discover a severe problem of trajectory overlapping in all analyzed datasets, highlighting that predictors memorize trajectories while having limited generalization capacities. We thus propose a methodology to rerank the outputs of the next-location predictors based on spatial mobility patterns. With these techniques, we significantly improve the predictors' generalization capability, with a relative improvement on the accuracy up to 96.15% on the trajectories that cannot be memorized (i.e., low overlap with the training set).
- 16 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 33 (9) , 3258-3269
Land Use Classification With Point of Interests and Structural Patterns
In this paper, we present a framework for performing automatic analysis of Land Use Zones based on Location-Based Social Networks (LBSNs). We model city areas using a hierarchical structure of POIs extracted from foursquare. We encode such structures in kernel machines, e.g., Support Vector Machines, using a new Tree Kernel, i.e., the Hierarchical POI Kernel (HPK), which can take the importance of the individual POIs into account during the substructure matching. This way, HPK projects structures in the space of all their possible substructures such that each dimension corresponds to a semantic structural feature, weighted according to the discriminative power of POIs . We generated four different datasets for the following cities: Barcelona, Lisbon, Amsterdam and Milan, where we trained and tested our models. The results show that our approach largely outperforms previous work and standard baseline built on simple features, such as counts of different POIs. Finally, we apply a mining algorithm to extract the most relevant features (tree fragments) from the implicit TK space according to the weights the kernel machine assigned to them. Our approach can produce an explicit set of representative features that can be used to classify and characterize urban areas.
- 16 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 33 (9) , 3258-3269
Land Use Classification With Point of Interests and Structural Patterns
In this paper, we present a framework for performing automatic analysis of Land Use Zones based on Location-Based Social Networks (LBSNs). We model city areas using a hierarchical structure of POIs extracted from foursquare. We encode such structures in kernel machines, e.g., Support Vector Machines, using a new Tree Kernel, i.e., the Hierarchical POI Kernel (HPK), which can take the importance of the individual POIs into account during the substructure matching. This way, HPK projects structures in the space of all their possible substructures such that each dimension corresponds to a semantic structural feature, weighted according to the discriminative power of POIs . We generated four different datasets for the following cities: Barcelona, Lisbon, Amsterdam and Milan, where we trained and tested our models. The results show that our approach largely outperforms previous work and standard baseline built on simple features, such as counts of different POIs. Finally, we apply a mining algorithm to extract the most relevant features (tree fragments) from the implicit TK space according to the weights the kernel machine assigned to them. Our approach can produce an explicit set of representative features that can be used to classify and characterize urban areas.
- 19 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 21 (7) , 2980-2989
Modelling Taxi Drivers’ Behaviour for the Next Destination Prediction
In this paper, we study how to model taxi drivers' behavior and geographical information for an interesting and challenging task: the next destination prediction in a taxi journey. Predicting the next location is a well-studied problem in human mobility, which finds several applications in real-world scenarios, from optimizing the efficiency of electronic dispatching systems to predicting and reducing the traffic jam. This task is normally modeled as a multiclass classification problem, where the goal is to select, among a set of already known locations, the next taxi destination. We present a Recurrent Neural Network (RNN) approach that models the taxi drivers' behavior and encodes the semantics of visited locations by using geographical information from Location-Based Social Networks (LBSNs). In particular, the RNNs are trained to predict the exact coordinates of the next destination, overcoming the problem of producing, in output, a limited set of locations, seen during the training phase. The proposed approach was tested on the ECML/PKDD Discovery Challenge 2015 dataset--based on the city of Porto--, obtaining better results with respect to the competition winner, whilst using less information, and on Manhattan and San Francisco datasets.
- 19 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 21 (7) , 2980-2989
Modelling Taxi Drivers’ Behaviour for the Next Destination Prediction
In this paper, we study how to model taxi drivers' behavior and geographical information for an interesting and challenging task: the next destination prediction in a taxi journey. Predicting the next location is a well-studied problem in human mobility, which finds several applications in real-world scenarios, from optimizing the efficiency of electronic dispatching systems to predicting and reducing the traffic jam. This task is normally modeled as a multiclass classification problem, where the goal is to select, among a set of already known locations, the next taxi destination. We present a Recurrent Neural Network (RNN) approach that models the taxi drivers' behavior and encodes the semantics of visited locations by using geographical information from Location-Based Social Networks (LBSNs). In particular, the RNNs are trained to predict the exact coordinates of the next destination, overcoming the problem of producing, in output, a limited set of locations, seen during the training phase. The proposed approach was tested on the ECML/PKDD Discovery Challenge 2015 dataset--based on the city of Porto--, obtaining better results with respect to the competition winner, whilst using less information, and on Manhattan and San Francisco datasets.
- Open Access
Modeling Taxi Drivers' Behaviour for the Next Destination Prediction
In this paper, we study how to model taxi drivers' behaviour and geographical information for an interesting and challenging task: the next destination prediction in a taxi journey. Predicting the next location is a well studied problem in human mobility, which finds several applications in real-world scenarios, from optimizing the efficiency of electronic dispatching systems to predicting and reducing the traffic jam. This task is normally modeled as a multiclass classification problem, where the goal is to select, among a set of already known locations, the next taxi destination. We present a Recurrent Neural Network (RNN) approach that models the taxi drivers' behaviour and encodes the semantics of visited locations by using geographical information from Location-Based Social Networks (LBSNs). In particular, RNNs are trained to predict the exact coordinates of the next destination, overcoming the problem of producing, in output, a limited set of locations, seen during the training phase. The proposed approach was tested on the ECML/PKDD Discovery Challenge 2015 dataset - based on the city of Porto -, obtaining better results with respect to the competition winner, whilst using less information, and on Manhattan and San Francisco datasets.
Open AccessModeling Taxi Drivers' Behaviour for the Next Destination Prediction
In this paper, we study how to model taxi drivers' behaviour and geographical information for an interesting and challenging task: the next destination prediction in a taxi journey. Predicting the next location is a well studied problem in human mobility, which finds several applications in real-world scenarios, from optimizing the efficiency of electronic dispatching systems to predicting and reducing the traffic jam. This task is normally modeled as a multiclass classification problem, where the goal is to select, among a set of already known locations, the next taxi destination. We present a Recurrent Neural Network (RNN) approach that models the taxi drivers' behaviour and encodes the semantics of visited locations by using geographical information from Location-Based Social Networks (LBSNs). In particular, RNNs are trained to predict the exact coordinates of the next destination, overcoming the problem of producing, in output, a limited set of locations, seen during the training phase. The proposed approach was tested on the ECML/PKDD Discovery Challenge 2015 dataset - based on the city of Porto -, obtaining better results with respect to the competition winner, whilst using less information, and on Manhattan and San Francisco datasets.
- 30 December 2017
- Published by Springer Nature
- p. 279-291
Structural Semantic Models for Automatic Analysis of Urban Areas
- 30 December 2017
- Published by Springer Nature
- p. 279-291
Structural Semantic Models for Automatic Analysis of Urban Areas
- Open Access
- 24 October 2017
- Published by Springer Nature in EPJ Data Science
- Vol. 6 (1) , 27
Are you getting sick? Predicting influenza-like symptoms using human mobility behaviors
Understanding and modeling the mobility of individuals is of paramount importance for public health. In particular, mobility characterization is key to predict the spatial and temporal diffusion of human-transmitted infections. However, the mobility behavior of a person can also reveal relevant information about her/his health conditions. In this paper, we study the impact of people mobility behaviors for predicting the future presence of flu-like and cold symptoms (i.e. fever, sore throat, cough, shortness of breath, headache, muscle pain, malaise, and cold). To this end, we use the mobility traces from mobile phones and the daily self-reported flu-like and cold symptoms of 29 individuals from February 20, 2013 to March 21, 2013. First of all, we demonstrate that daily symptoms of an individual can be predicted by using his/her mobility trace characteristics (e.g. total displacement, radius of gyration, number of unique visited places, etc.). Then, we present and validate models that are able to successfully predict the future presence of symptoms by analyzing the mobility patterns of our individuals. The proposed methodology could have a societal impact opening the way to customized mobile phone applications, which may detect and suggest to the user specific actions in order to prevent disease spreading and minimize the risk of contagion.
- 24 October 2017
- Published by Springer Nature in EPJ Data Science
- Vol. 6 (1) , 27
Open AccessAre you getting sick? Predicting influenza-like symptoms using human mobility behaviors
Understanding and modeling the mobility of individuals is of paramount importance for public health. In particular, mobility characterization is key to predict the spatial and temporal diffusion of human-transmitted infections. However, the mobility behavior of a person can also reveal relevant information about her/his health conditions. In this paper, we study the impact of people mobility behaviors for predicting the future presence of flu-like and cold symptoms (i.e. fever, sore throat, cough, shortness of breath, headache, muscle pain, malaise, and cold). To this end, we use the mobility traces from mobile phones and the daily self-reported flu-like and cold symptoms of 29 individuals from February 20, 2013 to March 21, 2013. First of all, we demonstrate that daily symptoms of an individual can be predicted by using his/her mobility trace characteristics (e.g. total displacement, radius of gyration, number of unique visited places, etc.). Then, we present and validate models that are able to successfully predict the future presence of symptoms by analyzing the mobility patterns of our individuals. The proposed methodology could have a societal impact opening the way to customized mobile phone applications, which may detect and suggest to the user specific actions in order to prevent disease spreading and minimize the risk of contagion.
- Open Access
- 1 January 2017
- Published by OpenEdition
- p. 7-11
Predicting Land Use of Italian Cities using Structural Semantic Models
We propose a hierarchical semantic representation of urban areas extracted from a social network to classify the most predominant land use, which is a very common task in urban computing. We encode geosocial data from Location-Based Social Networks with standard feature vectors and a conceptual tree structure that we call Geo-Tree. We use the latter in kernel machines, which can thus perform accurate classification, exploiting hierarchical substructure of concepts as features. Our comparative study on three datasets extracted from Milan, Rome and Naples shows that Tree Kernels applied to Geo-Trees are very effective improving the state of the art.
- 1 January 2017
- Published by OpenEdition
- p. 7-11
Open AccessPredicting Land Use of Italian Cities using Structural Semantic Models
We propose a hierarchical semantic representation of urban areas extracted from a social network to classify the most predominant land use, which is a very common task in urban computing. We encode geosocial data from Location-Based Social Networks with standard feature vectors and a conceptual tree structure that we call Geo-Tree. We use the latter in kernel machines, which can thus perform accurate classification, exploiting hierarchical substructure of concepts as features. Our comparative study on three datasets extracted from Milan, Rome and Naples shows that Tree Kernels applied to Geo-Trees are very effective improving the state of the art.
- 1 January 2015
- Published by Springer Nature
- p. 556-561
Learning to Rank Aggregated Answers for Crossword Puzzles
- 1 January 2015
- Published by Springer Nature
- p. 556-561
Learning to Rank Aggregated Answers for Crossword Puzzles