Papers by Nicola Barbieri
Given a directed social graph and a set of past information cascades observed over the graph, we ... more Given a directed social graph and a set of past information cascades observed over the graph, we study the novel problem of detecting modules of the graph (communities of nodes), \emph{that also explain the cascades}. Our key observation is that both information propagation and social ties formation in a social network can be explained according to the same latent factor, which ultimately guide a user behavior within the network. Based on this observation, we propose the Community-Cascade Network (CCN) model, a stochastic mixture membership generative model that can fit, at the same time, the social graph and the observed set of cascades. Our model produces overlapping communities and for each node, its level of authority and passive interest in each community it belongs.
For learning the parameters of the CCN model, we devise a Generalized Expectation Maximization procedure. We then apply our model to real-world social networks and information cascades: the results witness the validity of the proposed CCN model, providing useful insights on its significance for analyzing social behavior.
We study social influence from a topic modeling perspective.
We introduce novel topic-aware ... more We study social influence from a topic modeling perspective.
We introduce novel topic-aware influence-driven propagation models that \emph{experimentally result to be more accurate in describing real-world cascades} than the standard propagation models studied in the literature. In particular, we first propose simple topic-aware extensions of the well-known Independent Cascade and Linear Threshold models. Next, we propose a different approach, explicitly modeling authoritativeness, influence and relevance under a topic-aware perspective. We devise methods to learn the parameters of the models from a dataset of past propagations. An extensive experimentation confirms the quality of the proposed models and learning schemes from the viewpoints of accuracy and influence maximization.
Balancing Prediction and Recommendation Accuracy: Hierarchical Latent Factors for Preference Data
The recommendation problem has been traditionally interpreted as a missing value prediction probl... more The recommendation problem has been traditionally interpreted as a missing value prediction problem (matrix completion)
The recommendation problem has been traditionally interpreted as a missing value prediction probl... more The recommendation problem has been traditionally interpreted as a missing value prediction problem, in which, given an active user, the system is asked to predict her preference for a set of items.
In this paper we extend the formulation of the User Rating Profile model, providing a Gibbs Sampl... more In this paper we extend the formulation of the User Rating Profile model, providing a Gibbs Sampling derivation for parameter estimation. Validation tests on Movielens data show that the proposed approach outperforms significantly the variational version in terms of both prediction accuracy and learning time. Gibbs Sampling provides a simple and flexible learning procedure which can be extended to include external evidence, in the form of soft constraints. More specifically, given apriori information about user-neighbors, we propose an effective regularization technique that drives the first sampling iterations pushing the model towards a state which better represents the user-neighborhoods specified in input.
Characterizing Relationships Through Co-Clustering a Probabilistic Approach
This paper presents a hierarchical probabilistic approach to collaborative filtering which allows... more This paper presents a hierarchical probabilistic approach to collaborative filtering which allows the discovery and analysis of both global patterns (i.e., tendency of some products of being 'universally appreciated') and local patterns ( tendency of users within a community to express a common preference on the same group of items). We reformulate the collaborative filtering approach as a clustering problem in a high-dimensional setting, and propose a probabilistic approach to model the data. The core of our approach is a co-clustering strategy, arranged in a hierarchical fashion: first, user communities are discovered, and then the information provided by each user community is used to discover topics, grouping items into categories. The resulting probabilistic framework can be used for detecting interesting relationships between users and items within user communities. The experimental evaluation shows that the proposed model achieves a competitive prediction accuracy with respect to the state-of-art collaborative filtering approaches.
This paper presents a probabilistic co-clustering approach to pattern discovery in preference dat... more This paper presents a probabilistic co-clustering approach to pattern discovery in preference data. We extended the original formulation of the block mixture model to handle rating data, the resulting model allows the simultaneous clustering of users and items in homogeneous user communities and item categories. The parameter of the model are determined using a variational approximation and a two-phase application of the EM algorithm. The experimental evaluation showed that proposed approach can be used both for rating prediction and pattern discovery tasks, such as the analysis of common trends within the same user community and the identification of interesting relationships between products belonging to the same item category. In particular, using Movie Lens data, we show how it is possibile to infer topics for each item category, and how to model community interests and transition among topics of interest.
Recommender systems are widely used in E-Commerce for making automatic suggestions of new items t... more Recommender systems are widely used in E-Commerce for making automatic suggestions of new items that could meet the interest of a given user. Collaborative Filtering approaches compute recommendations by assuming that users, who have shown similar behavior in the past, will share a common behavior in the future. According to this assumption, the most effective collaborative filtering techniques try to discover groups of similar users in order to infer the preferences of the group members. The purpose of this work is to show an empirical comparison of the main collaborative filtering approaches, namely Baseline, Nearest Neighbors, Latent Factor and Probabilistic models, focusing on their strengths and weaknesses. Data used for the analysis are a sample of the well-known Netflix Prize database.
Uploads
Papers by Nicola Barbieri
For learning the parameters of the CCN model, we devise a Generalized Expectation Maximization procedure. We then apply our model to real-world social networks and information cascades: the results witness the validity of the proposed CCN model, providing useful insights on its significance for analyzing social behavior.
We introduce novel topic-aware influence-driven propagation models that \emph{experimentally result to be more accurate in describing real-world cascades} than the standard propagation models studied in the literature. In particular, we first propose simple topic-aware extensions of the well-known Independent Cascade and Linear Threshold models. Next, we propose a different approach, explicitly modeling authoritativeness, influence and relevance under a topic-aware perspective. We devise methods to learn the parameters of the models from a dataset of past propagations. An extensive experimentation confirms the quality of the proposed models and learning schemes from the viewpoints of accuracy and influence maximization.