As Large Language Models (LLMs) have reached human-like fluency and coherence, distinguishing machine-generated text (MGT) from human-written content becomes increasingly difficult.While early efforts in MGT detection have focused on binary classification, the growing landscape and diversity of LLMs require a more fine-grained yet challenging authorship attribution (AA), i.e., being able to identify the precise generator (LLM or human) behind a text.However, AA remains nowadays confined to a monolingual setting, with English being the most investigated one, overlooking the multilingual nature and usage of modern LLMs.In this work, we introduce the problem of Multilingual Authorship Attribution, which involves attributing texts to human or multiple LLM generators across diverse languages.Focusing on 18 languages-covering multiple families and writing scripts-and 8 generators (7 LLMs and the human-authored class), we investigate the multilingual suitability of monolingual AA methods in terms of their crosslingual transferability, and the impact of generators on attribution performance.Our results reveal that while certain monolingual AA methods can be adapted to multilingual settings, significant limitations and challenges remain, particularly in transferring across diverse language families, underscoring the complexity of multilingual AA and the need for more robust approaches to better match real-world scenarios.

The rapid growth of Non-Fungible Tokens (NFTs) and the extensive trading activities associated with such an intriguing domain led to the emergence of large-scale and interconnected transaction networks involving the most prominent NFT markets. Despite such interdependencies representing an inestimable source of information for the proper understanding of the NFT landscape, previous studies treated each market separately, overlooking relevant phenomena. In this study, we explore a multilayer network modeling approach to analyze transactions in multiple NFT markets. We reveal previously unnoticed macroscopic and mesoscopic traits by investigating indicators that discern whether markets are independent or linked: users trading NFTs are organized in cross-market communities where multi-market users act as bridges across marketplaces, adapting to the diverse nature of the markets they operate in. We also conduct an in-depth examination of such multi-market users, studying their specific activity patterns that leave a distinctive mark on the system: the majority of multi-market users well differentiate their earnings and expenses among the markets, while a fraction of them is directed toward a more polarized money allocation based on the typology of the markets. By offering a fresh perspective on this intricate financial system and emphasizing the importance of perceiving the NFT markets as a unique and interconnected world, our study paves the way for further contributions aimed at unraveling the complexity of cryptosystems and understanding the latent phenomena across NFT markets.

Link prediction algorithms for multilayer networks are in principle required to effectively account for the entire layered structure while capturing the unique contexts offered by each layer. However, many existing approaches excel at predicting specific links in certain layers but struggle with others, as they fail to effectively leverage the diverse information encoded across different network layers. In this paper, we present MoE-ML-LP , the first Mixture-of-Experts (MoE) framework specifically designed for multilayer link prediction. Building on top of multilayer heuristics for link prediction, MoE-ML-LP synthesizes the decisions taken by diverse experts, resulting in significantly enhanced predictive capabilities. Our extensive experimental evaluation on real-world and synthetic networks demonstrates that MoE-ML-LP consistently outperforms several baselines and competing methods, achieving remarkable improvements of +60% in Mean Reciprocal Rank, +82% in Hits@1, +55% in Hits@5, and +41% in Hits@10. Furthermore, MoE-ML-LP features a modular architecture that enables the seamless integration of newly developed experts without necessitating the re-training of the entire framework, fostering efficiency and scalability to new experts, paving the way for future advancements in link prediction.

Abstract Polarization is common in social systems, where individuals tend to form cohesive groups that oppose each other. Signed networks, with positive edges representing agreement and negative edges representing disagreement, provide a natural model for studying such dynamics. The 2-Polarized-Communities problem ( 2pc ) was recently introduced to detect a single pair of polarized communities by maximizing a Rayleigh quotient that balances intra-community agreement and inter-community disagreement. However, real signed networks usually host multiple, coexisting axes of conflict, often with communities that overlap. Existing extension of 2pc to multiple communities or find-and-remove heuristics, either rely on the restrictive assumption that every polarized community is in conflict with all the others, or enforce disjoint solutions–thus failing to capture the nuanced structures observed in real networks. In this paper, we introduce the Diverse top-k-pc problem, which is the first principled formulation of top- k polarized communities with controlled overlap. Our formulation extends the 2pc polarity objective by incorporating diversity terms directly into the denominator of the Rayleigh quotient, yielding a generalized objective that jointly promotes polarity and diversity. We design a greedy sequential algorithm that solves a generalized eigenvector problem at each step, efficiently discovering diverse polarized pairs. Experiments on both real-world and synthetic signed networks demonstrate that our approach identifies multiple meaningful and overlapping pairs of polarized communities, outperforming natural baselines while scaling to large graphs.

Signed networks represent interactions among users (nodes), with edges labeled as positive for friendly relations and negative for antagonistic ones. The 2-Polarized-Communities ( 2pc ) combinatorial optimization problem seeks two disjoint polarized communities in a signed network, so as to satisfy three conditions: most edges within each community are positive, most edges between communities are negative, and the number of edges satisfying these conditions is high compared to the number of nodes in the communities. The Densest Subgraph ( ds ) problem in unsigned networks consists in finding a subgraph that exhibits maximum ratio between number of edges and number of nodes. Although the 2pc problem intuitively suggests finding a dense subgraph, no prior work has explored the implicitly optimized density measure or algorithmic methods from the rich, yet distinct, literature on the ds problem (in unsigned networks) and applied them to 2pc . This work bridges this gap by formally establishing a link between the two problems and introducing a highly efficient and effective greedy algorithm inspired by ds methods to solve 2pc . Experimental results on synthetic and real datasets demonstrate the superior performance of our method compared to competing approaches in terms of both accuracy and efficiency.

The emergence of unveiling human-like behaviors in Large Language Models (LLMs) has led to a closer connection between NLP and human psychology. However, research on the personalities exhibited by LLMs has largely been confined to limited investigations using individual psychological tests, primarily focusing on a small number of commercially licensed LLMs. This approach overlooks the extensive use and significant advancements observed in open-source LLMs. This work aims to address both the above limitations by conducting an in-depth investigation of a significant body of 12 LLM Agents based on the most representative Open models, through the two most well-known psychological assessment tests, namely Myers-Briggs Type Indicator (MBTI) and Big Five Inventory (BFI). Our approach involves evaluating the intrinsic personality traits of LLM agents and determining the extent to which these agents can mimic human personalities when conditioned by specific personalities and roles. Our findings unveil that (i) each LLM agent showcases distinct human personalities; (ii) personality-conditioned prompting produces varying effects on the agents, with only few successfully mirroring the imposed personality, while most of them being ``closed-minded'' (i.e., they retain their intrinsic traits); and (iii) combining role and personality conditioning can enhance the agents' ability to mimic human personalities. Our work represents a step up in understanding the dense relationship between NLP and human psychology through the lens of LLMs.

Morality serves as the foundation of societal structure, guiding legal systems, shaping cultural values, and influencing individual self-perception. With the rise and pervasiveness of generative AI tools, and particularly Large Language Models (LLMs), concerns arise regarding how these tools capture and potentially alter moral dimensions through machine-generated text manipulation. Based on the Moral Foundation Theory, our work investigates this topic by analyzing the behavior of 12 LLMs among the most widely used Open and uncensored (i.e., ”abliterated”) models, and leveraging human-annotated datasets used in moral-related analysis. Results have shown varying levels of alteration of moral expressions depending on the type of text modification task and moral-related conditioning prompt.

The way the media report on legal cases can significantly shape public opinion, often embedding subtle biases that influence societal views on justice, fairness, and morality. Analyzing these narratives requires a holistic approach that captures their emotional tone, moral framing, and the specific events they convey. In this work, we introduce E2MoCase, a novel dataset that enables integrated analysis of emotions, morality, and events within legal narratives and media coverage. We leverage NLP models to extract events and predict morality and emotions, providing a multidimensional perspective on how legal cases are portrayed in news articles. Our experimental evaluation showed that E2MoCase is beneficial for addressing emotion- and morality-based tasks, which is also confirmed by a human evaluation of the annotations.

We present PersonaGen, a novel dataset for investigating persona-driven machine-generated text (MGT) produced by Open Large Language Models (OLLMS). PersonaGen is specifically designed to investigate how synthetic persona profiles affect, guide, or manifest in MGT. We built PersonaGen by pairing curated persona-profiles (i.e., description of characteristics, background, and goals) across eight thematic domains (e.g., Physics, Education, Medicine) with prompts covering various narrative or opinion-style content (e.g., stories, commonsense). Open-ended generations were produced by six representative OLLMs, yielding a total of 1.44 million persona-driven generations. PersonaGen supports multiple research tasks, such as machine-generated text attribution, persona category detection, and persona profile identification, thus providing a valuable resource for studying LLM controllability and role-playing behavior, as well as the impact of persona profile conditioning in downstream tasks. We have released PersonaGen on the Hugging Face platform at https://doi.org/10.57967/hf/5805.

Moralities, emotions, and events are complex aspects of human cognition, which are often treated separately since capturing their combined effects is challenging, especially due to the lack of annotated data. Leveraging their interrelations hence becomes crucial for advancing the understanding of human moral behaviors. In this work, we propose ME2-BERT, the first holistic framework for fine-tuning a pre-trained language model like BERT to the task of moral foundation prediction. ME2-BERT integrates events and emotions for learning domain-invariant morality-relevant text representations. Our extensive experiments show that ME2-BERT outperforms existing state-of-the-art methods for moral foundation prediction, with an average increase up to 35% in the out-of-domain scenario.

Open Large Language Models (OLLMs) are increasingly leveraged in generative AI applications, posing new challenges for detecting their outputs.We propose OpenTuringBench, a new benchmark based on OLLMs, designed to train and evaluate machine-generated text detectors on the Turing Test and Authorship Attribution problems.OpenTuringBench focuses on a representative set of OLLMs, and features a number of challenging evaluation tasks, including human/machine-manipulated texts, outof-domain texts, and texts from previously unseen models.We also provide OTBDetector, a contrastive learning framework to detect and attribute OLLM-based machine-generated texts.Results highlight the relevance and varying degrees of difficulty of the OpenTuringBench tasks, with our detector achieving remarkable capabilities across the various tasks and outperforming most existing detectors.

The fervor for Non-Fungible Tokens (NFTs) attracted countless creators, leading to a Big Bang of digital assets driven by latent or explicit forms of inspiration, as in many creative processes. This work exploits Vision Transformers and graph-based modeling to delve into visual inspiration phenomena between NFTs over the years, i.e., the visual influence that can be detected whenever an NFT appears to be visually close to another that was published earlier in the market. Our goals include unveiling the main structural traits that shape visual inspiration networks, exploring the interrelation between visual inspiration and asset performances, investigating crypto influence on inspiration processes, and explaining the inspiration relationships among NFTs. Our findings unveil how the pervasiveness of inspiration led to a temporary saturation of the visual feature space, the impact of the dichotomy between inspiring and inspired NFTs on their financial performance, and an intrinsic self-regulatory mechanism between markets and inspiration waves. Our work can serve as a starting point for gaining a broader view of the evolution of Web3.

The significant progress in the development of Large Language Models has contributed to blurring the distinction between human and AI-generated text. The increasing pervasiveness of AI-generated text and the difficulty in detecting it poses new challenges for our society. In this paper, we tackle the problem of detecting and attributing AI-generated text by proposing WhosAI, a triplet-network contrastive learning framework designed to predict whether a given input text has been generated by humans or AI and to unveil the authorship of the text. Unlike most existing approaches, our proposed framework is conceived to learn semantic similarity representations from multiple generators at once, thus equally handling both detection and attribution tasks. Furthermore, WhosAI is model-agnostic and scalable to the release of new AI text-generation models by incorporating their generated instances into the embedding space learned by our framework. Experimental results on the TuringBench benchmark of 200K news articles show that our proposed framework achieves outstanding results in both the Turing Test and Authorship Attribution tasks, outperforming all the methods listed in the TuringBench benchmark leaderboards.

Link prediction has traditionally been studied in the context of simple graphs, although real-world networks are inherently complex as they are often comprised of multiple interconnected components, or layers. Predicting links in such network systems, or multilayer networks, require to consider both the internal structure of a target layer as well as the structure of the other layers in a network, in addition to layer-specific node-attributes when available. This problem poses several challenges, even for graph neural network based approaches despite their successful and wide application to a variety of graph learning problems. In this work, we aim to fill a lack of multilayer graph representation learning methods designed for link prediction. Our proposal is a novel neural-network-based learning framework for link prediction on (attributed) multilayer networks, whose key idea is to combine (i) pairwise similarities of multilayer node embeddings learned by a graph neural network model, and (ii) structural features learned from both within-layer and across-layer link information based on overlapping multilayer neighborhoods. Extensive experimental results have shown that our framework consistently outperforms both single-layer and multilayer methods for link prediction on popular real-world multilayer networks, with an average percentage increase in AUC up to 38%. We make source code and evaluation data available at https://mlnteam-unical.github.io/resources/.

Active learning is focused on minimizing the effort required to obtain labeled data by iteratively choosing fresh data samples for training a machine learning model. One of the primary challenges in active learning involves the selection of the most informative instances for labeling by an annotation oracle at each iteration. A viable approach is to develop an active learning strategy that aligns with the performance of a meta-learning model. This strategy evaluates the quality of previously selected instances and subsequently trains a machine learning model to predict the quality of instances to be labeled in the current iteration. This paper introduces a novel approach to learning for active learning, wherein instances are chosen for labeling based on their potential to induce the most substantial change in the current classifier. We explore various strategies for assessing the significance of an instance, taking into account variations in the learning gradient of the classification model. Our approach can be applied to any classifier that can be trained using gradient descent optimization. Here, we present a formulation that leverages a deep neural network model, which has not been extensively explored in existing learning-to-active-learn methodologies. Through experimental validation, our approach demonstrates promising results, especially in scenarios where there are limited initially labeled instances, particularly when the number of labeled instances per class is extremely limited.

Abstract Signed graphs are a model to depict friendly (positive) or antagonistic (negative) interactions (edges) among users (nodes). 2-Polarized-Communities (2pc) is a well-established combinatorial-optimization problem whose goal is to find two polarized communities from a signed graph, i.e., two subsets of nodes (disjoint, but not necessarily covering the entire node set) which exhibit a high number of both intra-community positive edges and negative inter-community edges. The state of the art in 2pc suffers from the limitations that (i) existing methods rely on a single (optimal) solution to a continuous relaxation of the problem in order to produce the ultimate discrete solution via rounding, and (ii) 2pc objective function comes with no control on size balance among communities. In this paper, we provide advances to the 2pc problem by addressing both these limitations, with a twofold contribution. First, we devise a novel neural approach that allows for soundly and elegantly explore a variety of suboptimal solutions to the relaxed 2pc problem, so as to pick the one that leads to the best discrete solution after rounding. Second, we introduce a generalization of 2pc objective function – termed $$\gamma $$ γ -polarity – which fosters size balance among communities, and we incorporate it into the proposed machine-learning framework. Extensive experiments attest high accuracy of our approach, its superiority over the state of the art, and capability of function $$\gamma $$ γ -polarity to discover high-quality size-balanced communities.

In this work, we present SONAR, a web-based tool for multimodal exploration of Non-Fungible Token (NFT) inspiration networks. SONAR is conceived to support both creators and traders in the emerging Web3 by providing an interactive visualization of the inspiration-driven connections between NFTs, at both individual level and collection level. SONAR can hence be useful to identify new investment opportunities as well as anomalous inspirations. To demonstrate SONAR's capabilities, we present an application to the largest and most representative dataset concerning the NFT landscape to date, showing how our proposed tool can scale and ensure high-level user experience up to millions of edges.

Non-Fungible Tokens (NFTs) represent deeds of ownership, based on blockchain technologies and smart contracts, of unique crypto assets on digital art forms (e.g., artworks or collectibles). In the spotlight after skyrocketing in 2021, NFTs have attracted the attention of crypto enthusiasts and investors intent on placing promising investments in this profitable market. However, the NFT financial performance prediction has not been widely explored to date.

Abstract Given a graph whose edges are assigned positive-type and negative-type weights, the problem of correlation clustering aims at grouping the graph vertices so as to minimize (resp. maximize) the sum of negative-type (resp. positive-type) intra-cluster weights plus the sum of positive-type (resp. negative-type) inter-cluster weights. In correlation clustering, it is typically assumed that the weights are readily available. This is a rather strong hypothesis, which is unrealistic in several scenarios. To overcome this limitation, in this work we focus on the setting where edge weights of a correlation-clustering instance are unknown, and they have to be estimated in multiple rounds, while performing the clustering. The clustering solutions produced in the various rounds provide a feedback to properly adjust the weight estimates, and the goal is to maximize the cumulative quality of the clusterings. We tackle this problem by resorting to the reinforcement-learning paradigm, and, specifically, we design for the first time a Combinatorial Multi-Armed Bandit (CMAB) framework for correlation clustering. We provide a variety of contributions, namely (1) formulations of the minimization and maximization variants of correlation clustering in a CMAB setting; (2) adaptation of well-established CMAB algorithms to the correlation-clustering context; (3) regret analyses to theoretically bound the accuracy of these algorithms; (4) design of further (heuristic) algorithms to have the probability constraint satisfied at every round (key condition to soundly adopt efficient yet effective algorithms for correlation clustering as CMAB oracles); (5) extensive experimental comparison among a variety of both CMAB and non-CMAB approaches for correlation clustering.

A major challenge in active learning is to select the most informative instances to be labeled by an annotation oracle at each step. In this respect, one effective paradigm is to learn the active learning strategy that best suits the performance of a meta-learning model. This strategy first measures the quality of the instances selected in the previous steps and then trains a machine learning model that is used to predict the quality of instances to be labeled in the current step.In this paper, we propose a new approach of learning-to-active-learn that selects the instances to be labeled as the ones producing the maximum change to the current classifier. Our key idea is to select such instances according to their importance reflecting variations in the learning gradient of the classification model. Our approach can be instantiated with any classifier trainable via gradient descent optimization, and here we provide a formulation based on a deep neural network model, which has not deeply been investigated in existing learning-to-active-learn approaches. The experimental validation of our approach has shown promising results in scenarios characterized by relatively few initially labeled instances.

We present LawNet-Viz, a web-based tool for the modeling, analysis and visualization of law reference networks extracted from a statute law corpus. LawNet-Viz is designed to support legal research tasks and help legal professionals as well as laymen visually exploring the article connections built upon the explicit law references detected in the article contents. To demonstrate LawNet-Viz, we show its application to the Italian Civil Code (ICC), which exploits a recent BERT-based model fine-tuned on the ICC. LawNet-Viz is a system prototype that is planned for product development.

We study two novel clustering problems in which the pairwise interactions between entities are characterized by probability distributions and conditioned by external factors within the environment where the entities interact. This covers any scenario where a set of actions can alter the entities' interaction behavior. In particular, we consider the case where the interaction conditioning factors can be modeled as cluster memberships of entities in a graph and the goal is to partition a set of entities such as to maximize the overall vertex interactions or, equivalently, minimize the loss of interactions in the graph. We show that both problems are NP-hard and they are equivalent in terms of optimality. However, we focus on the minimization formulation as it enables the possibility of devising both practical and efficient approximation algorithms and heuristics. Experimental evaluation of our algorithms, on both synthetic and real network datasets, has shown evidence of their meaningfulness as well as superiority with respect to competing methods, both in terms of effectiveness and efficiency.

Community detection and evolution has been largely studied in the last few years, especially for network systems that are inherently dynamic and undergo different types of changes in their structure and organization in communities. Because of the inherent uncertainty and dynamicity in such network systems, we argue that temporal community detection problems can profitably be solved under a particular class of multi-armed bandit problems, namely combinatorial multi-armed bandit (CMAB). More specifically, we propose a CMAB-based methodology for the novel problem of dynamic consensus community detection, i.e., to compute a single community structure that is designed to encompass the whole information available in the sequence of observed temporal snapshots of a network in order to be representative of the knowledge available from community structures at the different time steps. Unlike existing approaches, our key idea is to produce a dynamic consensus solution for a temporal network to have unique capability of embedding both long-term changes in the community formation and newly observed community structures.

Respiratory diseases are among the most common causes of severe illness and death worldwide. Prevention and early diagnosis are essential to limit or even reverse the trend that characterizes the diffusion of such diseases. In this regard, the development of advanced computational tools for the analysis of respiratory auscultation sounds can become a game changer for detecting disease-related anomalies, or diseases themselves. In this work, we propose a novel learning framework for respiratory auscultation sound data. Our approach combines state-of-the-art feature extraction techniques and advanced deep-neural-network architectures. Remarkably, to the best of our knowledge, we are the first to model a recurrent-neural-network based learning framework to support the clinician in detecting respiratory diseases, at either level of abnormal sounds or pathology classes. Results obtained on the ICBHI benchmark dataset show that our approach outperforms competing methods on both anomaly-driven and pathology-driven prediction tasks, thus advancing the state-of-the-art in respiratory disease analysis.

Finding nearest neighbors is an important topic that has attracted much attention over the years and has applications in many fields, such as market basket analysis, plagiarism and anomaly detection, community detection, ligand-based virtual screening, etc. As data are easier and easier to collect, finding neighbors has become a potential bottleneck in analysis pipelines. Performing pairwise comparisons given the massive datasets of today is no longer feasible. The high computational complexity of the task has led researchers to develop approximate methods, which find many but not all of the nearest neighbors. Yet, for some types of data, efficient exact solutions have been found by carefully partitioning or filtering the search space in a way that avoids most unnecessary comparisons.

With the growing complexity of scenarios relating to online social networks (OSNs), there is an emergence of effective models and methods for understanding the characteristics and dynamics of multiple interconnected types of user relations. Profiles on different OSNs belonging to the same user can be linked using the multilayer structure, opening to unprecedented opportunities for user behavior analysis in a complex system. In this paper, we leverage the importance of studying the dichotomy between information-producers (contributors) and information-consumers (lurkers), and their interplay over a multilayer network, in order to effectively analyze such different roles a user may take on different OSNs. In this respect, we address the novel problem of identification and characterization of opposite behaviors that users may alternately exhibit over multiple layers of a complex network. We propose the first ranking method for alternate lurker-contributor behaviors on a multilayer OSN, dubbed mlALCR. Performance of mlALCR has been assessed quantitatively as well as qualitatively, and comparatively against methods designed for ranking either contributors or lurkers, on four real-world multilayer networks. Empirical evidence shows the significance and uniqueness of mlALCR in being able to mine alternate lurker-contributor behaviors over different layer networks.

Research on influence maximization ofter has to cope with marketing needs relating to the propagation of information towards specific users. However, little attention has been paid to the fact that the success of an information diffusion campaign might depend not only on the number of the initial influencers to be detected but also on theirdiversityw.r.t. the target of the campaign. Our main hypothesis is that if we learn seeds that are not only capable of influencing but also are linked to more diverse (groups of) users, then the influence triggers will be diversified as well, and hence the target users will get higher chance of being engaged. Upon this intuition, we define a novel problem, namedDiversity-sensitive Targeted Influence Maximization (DTIM), which assumes to model user diversity by exploiting only topological information within a social graph. To the best of our knowledge, we are the first to bring the concept of topology-driven diversity into targeted IM problems, for which we define two alternative definitions. Accordingly, we propose approximate solutions of DTIM, which detect a size-$k$set of users that maximizes the diversity-sensitive capital objective function, for a given selection of target users. We evaluate our DTIM methods on a special case of user engagement in online social networks, which concerns users who are not actively involved in the community life. Experimental evaluation on real networks has demonstrated the meaningfulness of our approach, also highlighting the opportunity of further development of solutions for DTIM applications.

Modularity for multilayer networks, also called multislice modularity, is parametric to a resolution factor and an inter-layer coupling factor. The former is useful to express layer-specific relevance and the latter quantifies the strength of node linkage across the layers of a network. However, such parameters can be set arbitrarily, thus discarding any structure information at graph or community level. Other issues are related to the inability of properly modeling order relations over the layers, which is required for dynamic networks.

Computational approaches to lurking behavior analysis in online social networks (OSNs) have been developed in the last few years. However, the complexity of the problem hints at the opportunity of learning from past lurking experiences as well as of using a variety of behavioral features, including any available information on the activity and interaction of lurkers and active users in an OSN. In this paper, we leverage this opportunity in a principled way, by proposing a machine-learning framework which, once trained on lurking/non-lurking examples from multiple OSNs, allows us to predict the ranking of unseen lurking behaviors, ultimately enabling the prioritization of user engagement tasks.

The problem of local community detection refers to the identification of a community starting from a query node and using limited information about the network structure. Existing methods for solving this problem however are not designed to deal with multilayer network models, which are becoming pervasive in many fields of science. In this work, we present the first method for local community detection in multilayer networks. Our method exploits both internal and external connectivity of the nodes in the community being constructed for a given seed, while accounting for different layer-specific topological information. Evaluation of the proposed method has been conducted on real-world multilayer networks.

The participation inequality phenomenon in online social networks between the niche of super contributors and the crowd of silent users, a.k.a. lurkers, has been witnessed in many domains. Within this view, understanding the role that lurkers take in the network is essential to develop innovative strategies to delurk them, i.e., to engage such users into a more active participation in the social network life. In this work, we leverage the boundary spanning theory to enhance our understanding of lurking behaviors, with the goal of improving the task of delurking in social networks. Assuming the availability of a global community structure, we first analyze how lurkers are related to users that take the role of bridges between different communities, unveiling insights into the bridging nature of lurkers and their tendency to acquire information from outside their own community. Moreover, based on a targeted influence maximization method designed for delurking, we also analyze how the learning of users that can best engage lurkers is related to the community structure. We found that the best users to engage lurkers belonging to any particular community, are more often found outside that community, and more specifically they are located in the adjacent communities.

Lurkers are silent members of a social network (SN) who gain benefit from others' information without significantly giving back to the community. The study of lurking behaviors in SNs is nonetheless important, since these users acquire knowledge from the community, and as such they are social capital holders. Within this view, a major goal is to delurk such users, i.e., to encourage them to more actively be involved in the SN. Despite delurking strategies have been conceptualized in social science and human-computer interaction research, no computational approach has been so far defined to turn lurkers into active participants in the SN. In this work we fill this gap by presenting a delurking-oriented targeted influence maximization problem under the linear threshold (LT) model. We define a novel objective function, in terms of the lurking scores associated with the nodes in the final active set, and we show it is monotone and submodular. We provide an approximate solution by developing a greedy algorithm, named DEvOTION, which computes a k- node set that maximizes the value of the delurking-capital-based objective function, for a given minimum lurking score threshold. Results on SN datasets of different sizes have demonstrated the significance of our delurking approach via LT-based targeted influence maximization.

Multilingual document classification is often addressed by approaches that rely on language-specific resources (e.g., bilingual dictionaries and machine translation tools) to evaluate cross-lingual document similarities. However, the required transformations may alter the original document semantics, raising additional issues to the known difficulty of obtaining high-quality labeled datasets. To overcome such issues we propose a new framework for multilingual document classification under a transductive learning setting. We exploit a large-scale multilingual knowledge base, BabelNet, to support the modeling of different language-written documents into a common conceptual space, without requiring any language translation process. We resort to a state-of-the-art transductive learner to produce the document classification. Results on two real-world multilingual corpora have highlighted the effectiveness of the proposed document model w.r.t. document representations usually involved in multilingual and cross-lingual analysis, and the robustness of the transductive setting for multilingual document classification. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

The proliferation of computing devices in recent years has dramatically changed the way people work, play, communicate, and access information. The personal computer (PC) now has to compete with smartphones, tablets, and other devices for tasks it used to be the default device for. Understanding how PC usage evolves over time can help provide the best overall user experience for current customers, can help determine when they need brand new systems vs. upgraded components, and can inform future product design to better anticipate user needs.

Mining the silent members, also called lurkers, of an online community has been recognized as an important problem that accompanies the extensive use of social networks. Existing solutions to the ranking of lurkers can aid understanding the lurking behaviors in social networks, however they ignore any information concerning the time dimension. In this work we push forward research in lurker mining by providing an analysis of temporal aspects that aims to unveil the behavior of lurkers and their interrelations with other users. Our analysis builds upon four research questions, which encompass relations between lurkers and inactive users, relations between lurkers and active users, the responsiveness behavior of lurkers, and the evolution of lurking trends across time. Evaluation has been conducted on Flickr, FriendFeed and Instagram networks.

A major challenge in document clustering research arises from the growing amount of text data written in different languages. Previous approaches depend on language-specific solutions (e.g., bilingual dictionaries, sequential machine translation) to evaluate document similarities, and the required transformations may alter the original document semantics. To cope with this issue we propose a new document clustering approach for multilingual corpora that (i) exploits a large-scale multilingual knowledge base, (ii) takes advantage of the multi-topic nature of the text documents, and (iii) employs a tensor-based model to deal with high dimensionality and sparseness. Results have shown the significance of our approach and its better performance w.r.t. classic document clustering approaches, in both a balanced and an unbalanced corpus evaluation.

The massive presence of silent members in online communities, the so-called lurkers, has long attracted the attention of researchers in social science, cognitive psychology, and computer-human interaction. However, the study of lurking phenomena represents an unexplored opportunity of research in data mining, information retrieval and related fields. In this paper, we take a first step towards the formal specification and analysis of lurking in social networks. Particularly, focusing on the network topology, we address the new problem of lurker ranking and propose the first centrality methods specifically conceived for ranking lurkers in social networks. Using Twitter and FriendFeed as cases in point, our methods' performance was evaluated against data-driven rankings as well as existing centrality methods, including the classic PageRank and alpha-centrality. Empirical evidence has shown the significance of our lurker ranking approach, which substantially differs from other methods in effectively identifying and ranking lurkers.

An emerging trend in research on recommender systems is the design of methods capable of recommending packages instead of single items. The problem is challenging due to a variety of critical aspects, including context-based and user-provided constraints for the items constituting a package, but also the high sparsity and limited accessibility of the primary data used to solve the problem. Most existing works on the topic have focused on a specific application domain (e.g., travel package recommendation), thus often providing ad-hoc solutions that cannot be adapted to other domains. By contrast, in this paper we propose a versatile package recommendation approach that is substantially independent of the peculiarities of a particular application domain. A key aspect in our framework is the exploitation of prior knowledge on the content type models of the packages being generated that express what the users expect from the recommendation task. Packages are learned for each package model, while the recommendation stage is accomplished by performing a PageRank-style method personalized w.r.t. the target user's preferences, possibly including a limited budget. Our developed method has been tested on a TripAdvisor dataset and compared with a recently proposed method for learning composite recommendations.

Clustering uncertain data has emerged as a challenging task in uncertain data management and mining. Thanks to a computational complexity advantage over other clustering paradigms, partitional clustering has been particularly studied and a number of algorithms have been developed. While existing proposals differ mainly in the notions of cluster centroid and clustering objective function, little attention has been given to an analysis of their characteristics and limits. In this work, we theoretically investigate major existing methods of partitional clustering, and alternatively propose a well-founded approach to clustering uncertain data based on a novel notion of cluster centroid. A cluster centroid is seen as an uncertain object defined in terms of a random variable whose realizations are derived based on all deterministic representations of the objects to be clustered. As demonstrated theoretically and experimentally, this allows for better representing a cluster of uncertain objects, thus supporting a consistently improved clustering performance while maintaining comparable efficiency with existing partitional clustering algorithms.

Projective Clustering Ensembles (PCE) are a very recent advance in data clustering research which combines the two powerful tools of clustering ensembles and projective clustering.Specifically, PCE enables clustering ensemble methods to handle ensembles composed by projective clustering solutions. PCE has been formalized as an optimization problem with either a two-objective or a single-objective function. Two-objective PCE has shown to generally produce more accurate clustering results than its single-objective counterpart, although it can handle the object-based and feature-based cluster representations only independently of one other. Moreover, both the early formulations of PCE do not follow any of the standard approaches of clustering ensembles, namely instance-based, cluster-based, and hybrid. In this paper, we propose an alternative formulation to the PCE problem which overcomes the above issues. We investigate the drawbacks of the early formulations of PCE and define a new single-objective formulation of the problem. This formulation is capable of treating the object- and feature-based cluster representations as a whole, essentially tying them in a distance computation between a projective clustering solution and a given ensemble. We propose two cluster-based algorithms for computing approximations to the proposed PCE formulation, which have the common merit of conforming to one of the standard approaches of clustering ensembles. Experiments on benchmark datasets have shown the significance of our PCE formulation, as both the proposed heuristics outperform existing PCE methods.

The PDF format represents the de facto standard for print-oriented documents. In this paper, we address the problem of wrapping PDF documents, which raises new challenges in several contexts of text data management. Our proposal is based on a novel bottom-up hierarchical wrapping approach that exploits fuzzy logic to handle the “uncertainty” which is intrinsic to the structure and presentation of PDF documents. A PDF wrapper is defined by specifying a set of group type definitions that impose a target structure to groups of tokens containing the required information. Constraints on token groupings are formulated as fuzzy conditions, which are defined on spatial and content predicates of tokens. We define a formal semantics for PDF wrappers and propose an algorithm for wrapper evaluation working in polynomial time with respect to the size of a PDF document. The proposed approach has been implemented in a wrapper generation system that offers visual capabilities to assist the designer in specifying and evaluating a PDF wrapper. Experimental results have shown good accuracy and applicability of our system to PDF documents of various domains.

Projective Clustering Ensembles (PCE) has recently been formulated to solve the problem of deriving a robust projective consensus clustering from an ensemble of projective clustering solutions. PCE is formalized as an optimization problem with either a two-objective or a single-objective function, depending on whether the object-based and the feature-based representations of the clusters in the ensemble are treated separately. A major result in is that single-objective PCE outperforms two-objective PCE in terms of efficiency, at the cost of lower accuracy in consensus clustering. In this paper, we enhance the single-objective PCE formulation, with the ultimate goal of providing more effective formulations capable of reducing the accuracy gap with the two-objective counterpart, while maintaining the efficiency advantages. We provide theoretical insights into the single-objective function, and introduce two heuristics that overcome the major limitations of the previous single-objective PCE formulation. Experimental evidence has demonstrated the significance of our proposed heuristics. In fact, results have not only confirmed a far better efficiency w.r.t. two-objective PCE, but have also shown the claimed improvements in accuracy of the consensus clustering obtained by the new single-objective PCE.

The increasing demand for dealing with uncertainty in data has led to the development of effective and efficient approaches in the data management and mining contexts. Clustering uncertain data objects has particularly attracted great attention in the data mining community. Most existing clustering methods however have urgently to come up with a number of issues, some of which are related to a poor efficiency mainly due to an expensive computation of the distance between uncertain objects. In this work, we propose a novel formulation to the problem of clustering uncertain objects, which allows for reaching accurate solutions by minimizing the variance of the mixture models that represent the clusters to be identified. We define a heuristic, MMVar, which exploits some analytical properties about the computation of variance for mixture models to compute local minima of the objective function at the basis of the proposed formulation. This characteristic allows MMVar to discard any distance measure between uncertain objects and, therefore, to achieve high efficiency. Experiments have shown that MMVar outperforms state-of-the-art algorithms from an efficiency viewpoint, while achieving better average performance in terms of accuracy.

Dealing with structure and content semantics underlying semistructured documents is challenging for any task of document management and knowledge discovery conceived for such data. In this work we address the novel problem of clustering semantically related XML documents according to their structure and content features. XML features are generated by enriching syntactic with semantic information based on a lexical knowledge base. The backbone of the proposed framework for the semantic clustering of XML documents is a data representation model that exploits the notion of tree tuple to identify semantically cohesive substructures in XML documents and represent them as transactional data. This framework is equipped with two clustering algorithms based on different paradigms, namely centroid-based partitional clustering and frequent-itemset-based hierarchical clustering. An extensive experimental evaluation was conducted on real data sets from various domains, showing the significance of our approach as a solution for the semantic clustering of XML documents.

Handling microarray data is particularly challenging mainly due to the high dimensionality of such data, which demands for computer-aided methods, and to the intrinsic difficulty of devising notions of proximity between spots of array traps. In this paper, we propose a new approach to modeling the probe-level uncertainty in microarray data that allows for a more expressive representation of the data and a more accurate processing. This approach is essentially based on a recently proposed method for uncertain data clustering. This method lies in a centroid-linkage-based agglomerative hierarchical algorithm, named U-AHC, and an information-theoretic-based distance measure between uncertain data . We have conducted experiments on four large microarray datasets, in order to assess effectiveness of the proposed clustering method. Experimental results have shown high quality results in terms of compactness of the clustering solutions.

Recent advances in data clustering concern clustering ensembles and projective clustering methods, each addressing different issues in clustering problems. In this paper, we consider for the first time the projective clustering ensemble (PCE) problem, whose main goal is to derive a proper projective consensus partition from an ensemble of projective clustering solutions. We formalize PCE as an optimization problem which does not rely on any particular clustering ensemble algorithm, and which has the ability to handle hard as well as soft data clustering, and different feature weightings. We provide two formulations for PCE, namely a two-objective and a single-objective problem, in which the object-based and feature-based representations of the ensemble solutions are taken into account differently. Experiments have demonstrated that the proposed methods for PCE show clear improvements in terms of accuracy of the output consensus partition.

Current deregulated energy market requires that utilities have to face challenging issues that mainly arise from conceiving new customercentric frameworks instead of early supplier-centric frameworks. Enel, a large international energy utility, is able to measure and store load profiles of their mass-market low-voltage (LV) customers in a flexible and effective way thanks to the well-established Telegestore project [3, 12].In this paper, we present a study on the characterization of LV customers based on their consumption data. A time series based model is used to suitably represent load profiles and enable the detection of their characteristic trends. Besides this primary data, we also exploit meta-data associated to the load profiles, which is useful to enrich a-priori knowledge on the customers. We conceived a clustering framework for detecting groups of customers having similar consumption behavior. We experimentally evaluated the proposed framework on a real application concerning the characterization of Enel customers according to their load profiles. Preliminary experiments have shown results which are significant in terms of clustering validity and potentially useful to practitioners from the Enel utility.

Clustering ensembles has been recently recognized as an emerging approach to provide more robust solutions to the data clustering problem.Current methods of clustering ensembles typically fall into instance-based, cluster-based, or hybrid approaches; however, most of such methods fail in discriminating among the various clusterings that participate to the ensemble.In this paper, we address the problem of weighting clustering ensembles by proposing general weighting approaches based on different implementations of the notion of diversity.We introduce three weighting schemes for clustering ensembles, called Single Weighting, Group Weighting and Dendrogram Weighting, which are independent of the particular method of clustering ensembles and designed to take into account correlations among the individual clustering solutions in different ways.We show how these schemes can be instantiated into any instance-based, cluster-based and hybrid clustering ensembles methods.Experiments have shown that the performance of the clustering ensembles algorithms increases when the proposed weighting schemes are employed.

Preprocessing mass spectrometry (MS) data has been recognized as a crucial preliminary phase in order to perform data management and knowledge discovery tasks on mass spectra. The huge dimensionality and heterogeneity of MS data make mandatory the use of tools that are able to guide the user in the MS preprocessing task. However, most MS preprocessing tools are typically designed to perform only some preprocessing steps and are strictly coupled with MS data analysis modules. In this paper, we present mass spectra preprocessing tool (MSPtool), a user-friendly versatile tool for preprocessing MS data. MSPtool provides the user with a wide set of MS preprocessing steps by means of an easy-to-use graphical interface. Also, this tool has been embedded in a time-series-based framework for MS data clustering.

In recent years there has been a growing interest in clustering uncertain data. In contrast to traditional, "sharp" data representation models, uncertain data objects can be represented in terms of an uncertainty region over which a probability density function (pdf) is defined. In this context, the focus has been mainly on partitional and density-based approaches, whereas hierarchical clustering schemes have drawn less attention. We propose a centroid-linkage-based agglomerative hierarchical algorithm for clustering uncertain objects, named U-AHC. The cluster merging criterion is based on an information-theoretic measure to compute the distance between cluster prototypes. These prototypes are represented as mixture densities that summarize the pdfs of all the uncertain objects in the clusters. Experiments have shown that our method outperforms state-of-the-art clustering algorithms from an accuracy viewpoint while achieving reasonably good efficiency.

This paper presents a methodology to mine spectra data based on time-series analysis. MALDI-TOF spectra are modelled as time series using a compact yet feature-rich representation scheme. Experiments show that classifying mass spectrometry series is effective and can be useful for identifying peaks in spectra that can be associated to discriminant proteins.

We present DSA - Derivative time series Segment Approximation, a novel representation model for time series designed for effective and efficient similarity search. DSA substantially exploits derivative estimation, segmentation and dimensionality reduction to meet at least the requirements of high sensitivity to main features (trends) of time series and robustness to outliers. Experiments show that DSA is drastically faster and still as good or better than the prominent state-of-the-art similarity methods.

The increasing availability of heterogeneous XML informative sources has raised a number of issues concerning how to represent and manage semistructured data. Although XML sources can exhibit proper structures and contents, differently annotated XML documents may in principle encode related semantics due to subjective definitions of markup tags. Discovering knowledge to infer semantic organization of XML documents has become a major challenge in XML data management. In this context, we address the problem of clustering XML data according to structure as well as content features enriched with lexical ontology knowledge. We propose a framework for clustering semantically cohesive XML structures based on a transactional representation model. Experiments on large real datasets give evidence that the proposed approach is highly effective in detecting groups of XML data that exhibit structure and/or content affinities.

We introduce a technique based on data mining algorithms for classifying incoming messages, as a basis for an overall architecture for maintenance and management of e-mail messages. We exploit clustering techniques for grouping structured and unstructured information extracted from e-mail messages in an unsupervised way, and exploit the resulting algorithm in the process of folder creation (and maintenance) and e-mail redirection. Some initial experimental results show the effectiveness of the technique, both from an efficiency and a quality-of-results viewpoint.