2014
Conference article
Unknown
The patterns of musical influence on the Last.Fm social network
Pennacchioli D., Rossetti G., Pappalardo L., Pedreschi D., Giannotti F., Coscia M.
One classic problem definition in social network analysis is the study of diffusion in networks, which enables us to tackle problems like favoring the adoption of positive technologies. Most of the attention has been turned to how to maximize the number of influenced nodes, but this approach misses the fact that different scenarios imply different diffusion dynamics, only slightly related to maximizing the number of nodes involved. In this paper we study the patterns of musical influence through a social network. First, we define a procedure to extract musical leaders, i.e. users who start the diffusion of new music albums through the social network. Second, we measure three different dimensions of musical influence: the Width, i.e. the ratio of neighbors influenced by a leader; the Depth, i.e. the degrees of separation from a leader to its influenced nodes; and the Strength, i.e. the intensity of the influence from a leader. We validate our results on a social network extracted from the Last.Fm music platform.Source: 22nd Italian Symposium on Advanced Database Systems, pp. 284–291, Castellammare di Stabia, Italy, 16-18 June 2014
Project(s): DATA SIM
Pennacchioli D., Rossetti G., Pappalardo L., Pedreschi D., Giannotti F., Coscia M.
One classic problem definition in social network analysis is the study of diffusion in networks, which enables us to tackle problems like favoring the adoption of positive technologies. Most of the attention has been turned to how to maximize the number of influenced nodes, but this approach misses the fact that different scenarios imply different diffusion dynamics, only slightly related to maximizing the number of nodes involved. In this paper we study the patterns of musical influence through a social network. First, we define a procedure to extract musical leaders, i.e. users who start the diffusion of new music albums through the social network. Second, we measure three different dimensions of musical influence: the Width, i.e. the ratio of neighbors influenced by a leader; the Depth, i.e. the degrees of separation from a leader to its influenced nodes; and the Strength, i.e. the intensity of the influence from a leader. We validate our results on a social network extracted from the Last.Fm music platform.Source: 22nd Italian Symposium on Advanced Database Systems, pp. 284–291, Castellammare di Stabia, Italy, 16-18 June 2014
Project(s): DATA SIM
See at: CNR ExploRA
2014
Conference article
Unknown
The purpose of motion: learning activities from individual mobility networks
Rinzivillo S., Gabrielli L., Nanni M., Pappalardo L., Pedreschi D., Giannotti F.
The large availability of mobility data allows us to investigate complex phenomena about human movement. However this adundance of data comes with few information about the purpose of movement. In this work we address the issue of activity recognition by introducing Activity-Based Cascading (ABC) classification. Such approach departs completely from probabilistic approaches for two main reasons. First, it exploits a set of structural features extracted from the Individual Mobility Network (IMN), a model able to capture the salient aspects of individual mobility. Second, it uses a cascading classification as a way to tackle the highly skewed frequency of activity classes. We show that our approach outperforms existing state-of-theart probabilistic methods. Since it reaches high precision, ABC classification represents a very reliable semantic amplifier for Big Data.Source: DSAA 2014 - The 2014 International Conference on Data Science and Advanced Analytics, Shanghai, China, 30 October - 1 November 2014
Rinzivillo S., Gabrielli L., Nanni M., Pappalardo L., Pedreschi D., Giannotti F.
The large availability of mobility data allows us to investigate complex phenomena about human movement. However this adundance of data comes with few information about the purpose of movement. In this work we address the issue of activity recognition by introducing Activity-Based Cascading (ABC) classification. Such approach departs completely from probabilistic approaches for two main reasons. First, it exploits a set of structural features extracted from the Individual Mobility Network (IMN), a model able to capture the salient aspects of individual mobility. Second, it uses a cascading classification as a way to tackle the highly skewed frequency of activity classes. We show that our approach outperforms existing state-of-theart probabilistic methods. Since it reaches high precision, ABC classification represents a very reliable semantic amplifier for Big Data.Source: DSAA 2014 - The 2014 International Conference on Data Science and Advanced Analytics, Shanghai, China, 30 October - 1 November 2014
See at: CNR ExploRA
2014
Contribution to book
Restricted
Evaluation of spatio-temporal microsimulation systems
Pappalardo L., Rinzivillo S., Christine K., Kochan B., May M., Schulz D., Simini F.
The increasing expressiveness of spatio-temporal microsimulation systems makes them attractive for a wide range of real world applications. However, the broad field of applications puts new challenges to the quality of microsimulation systems. They are no longer expected to reflect a few selected mobility characteristics but to be a realistic representation of the real world. In consequence, the validation of spatio-temporal microsimulations has to be deepened and to be especially moved towards a holistic view on movement validation. One advantage hereby is the easier availability of mobility data sets at present, which enables to validate many different aspects of movement behavior. However, these data sets bring their own challenges as the data may cover only a part of the observation space, differ in its temporal resolution or be not representative in all aspects. In addition, the definition of appropriate similarity measures, which capture the various mobility characteristics. The goal of this chapter is to pave the way for a novel, better and more detailed evaluation standard for spatio-temporal microsimulation systems. The chapter collects and structures various aspects that have to be considered for the validation and comparison of movement data. In addition, it assembles the state-of-the-art of existing validation techniques. It concludes with examples of using big data sources for the extraction and validation of movement characteristics outlining the research challenges that have yet to be conquered.Source: Data Science and Simulation in Transportation Research, edited by Davy Janssens, Ansar-Ul-Haque Yasar, Luk Knapen, pp. 141–146. Hershey: IGI Global, 2014
DOI: 10.4018/978-1-4666-4920-0.ch008
Metrics:
Pappalardo L., Rinzivillo S., Christine K., Kochan B., May M., Schulz D., Simini F.
The increasing expressiveness of spatio-temporal microsimulation systems makes them attractive for a wide range of real world applications. However, the broad field of applications puts new challenges to the quality of microsimulation systems. They are no longer expected to reflect a few selected mobility characteristics but to be a realistic representation of the real world. In consequence, the validation of spatio-temporal microsimulations has to be deepened and to be especially moved towards a holistic view on movement validation. One advantage hereby is the easier availability of mobility data sets at present, which enables to validate many different aspects of movement behavior. However, these data sets bring their own challenges as the data may cover only a part of the observation space, differ in its temporal resolution or be not representative in all aspects. In addition, the definition of appropriate similarity measures, which capture the various mobility characteristics. The goal of this chapter is to pave the way for a novel, better and more detailed evaluation standard for spatio-temporal microsimulation systems. The chapter collects and structures various aspects that have to be considered for the validation and comparison of movement data. In addition, it assembles the state-of-the-art of existing validation techniques. It concludes with examples of using big data sources for the extraction and validation of movement characteristics outlining the research challenges that have yet to be conquered.Source: Data Science and Simulation in Transportation Research, edited by Davy Janssens, Ansar-Ul-Haque Yasar, Luk Knapen, pp. 141–146. Hershey: IGI Global, 2014
DOI: 10.4018/978-1-4666-4920-0.ch008
Metrics:
See at:
doi.org 
| CNR ExploRA
2014
Conference article
Open Access
Mining efficient training patterns of non-professional cyclists (Discussion Paper)
Cintia P., Pappalardo L., Pedreschi D.
The recent emergence of the so called online social fitness open up new scenarios for fascinating challenges in the field of data sci- ence. Through these platforms, users can collect, monitor and share with friends their sport performance, with interesting details about heartrate, watt consumption and calories burned. The availability of this data, col- lected among a large number of users, gives us the possibility to explore new data mining applications. In the current work, we present the results of a study conducted on a sample of 29; 284 cyclists downloaded via APIs from the social fitness platform Strava.com. We defined two basic metrics: A measure of train- ing effort, that is how much a cyclist struggled during the workout; and a measure of training performance indicating the results achieved during the training. Although the average effort is weakly correlated with the average performance, by deeply investigating workouts time evolution and cyclists' training characteristics interesting findings came out. We found that athletes that better improve their performance follow precise training patterns usually referred as overcompensation theory, with alter- nation of stress peaks and rest periods. Studies and experiments related to such theory, up to now, have always been conducted by sports doctors on a few dozen professionals athletes. To the best of our knowledge, our study is the first corroboration on large scale of this theory.Source: SEBD 2014 - 22nd Italian Symposium on Advanced Database Systems, pp. 1–8, Sorrento Coast, Italy, 16-18 June 2014
Cintia P., Pappalardo L., Pedreschi D.
The recent emergence of the so called online social fitness open up new scenarios for fascinating challenges in the field of data sci- ence. Through these platforms, users can collect, monitor and share with friends their sport performance, with interesting details about heartrate, watt consumption and calories burned. The availability of this data, col- lected among a large number of users, gives us the possibility to explore new data mining applications. In the current work, we present the results of a study conducted on a sample of 29; 284 cyclists downloaded via APIs from the social fitness platform Strava.com. We defined two basic metrics: A measure of train- ing effort, that is how much a cyclist struggled during the workout; and a measure of training performance indicating the results achieved during the training. Although the average effort is weakly correlated with the average performance, by deeply investigating workouts time evolution and cyclists' training characteristics interesting findings came out. We found that athletes that better improve their performance follow precise training patterns usually referred as overcompensation theory, with alter- nation of stress peaks and rest periods. Studies and experiments related to such theory, up to now, have always been conducted by sports doctors on a few dozen professionals athletes. To the best of our knowledge, our study is the first corroboration on large scale of this theory.Source: SEBD 2014 - 22nd Italian Symposium on Advanced Database Systems, pp. 1–8, Sorrento Coast, Italy, 16-18 June 2014
See at:
toc.proceedings.com 
| CNR ExploRA