On the Aggression Diffusion Modeling and Minimization in Twitter

Aggression in online social networks has been studied mostly from the perspective of machine learning, which detects such behavior in a static context. However, the way aggression diffuses in the network has received little attention as it embeds modeling challenges. In fact, modeling how aggression propagates from one user to another is an important research topic, since it can enable effective aggression monitoring, especially in media platforms, which up to now apply simplistic user blocking techniques. In this article, we address aggression propagation modeling and minimization in Twitter, since it is a popular microblogging platform at which aggression had several onsets. We propose various methods building on two well-known diffusion models, Independent Cascade ( IC ) and Linear Threshold ( LT ), to study the aggression evolution in the social network. We experimentally investigate how well each method can model aggression propagation using real Twitter data, while varying parameters, such as seed users selection, graph edge weighting, users’ activation timing, and so on. It is found that the best performing strategies are the ones to select seed users with a degree-based approach, weigh user edges based on their social circles’ overlaps, and activate users according to their aggression levels. We further employ the best performing models to predict which ordinary real users could become aggressive (and vice versa) in the future, and achieve up to AUC = 0.89 in this prediction task. Finally, we investigate aggression minimization by launching competitive cascades to “inform” and “heal” aggressors. We show that IC and LT models can be used in aggression minimization, providing less intrusive alternatives to the blocking techniques currently employed by Twitter.

Incremental Group-Level Popularity Prediction in Online Social Networks

Predicting the popularity of web contents in online social networks is essential for many applications. However, existing works are usually under non-incremental settings. In other words, they have to rebuild models from scratch when new data occurs, which are inefficient in big data environments. It leads to an urgent need for incremental prediction, which can update previous results with new data and conduct prediction incrementally. Moreover, the promising direction of group-level popularity prediction has not been well treated, which explores fine-grained information while keeping a low cost. To this end, we identify the problem of incremental group-level popularity prediction, and propose a novel model IGPP to address it. We first predict the group-level popularity incrementally by exploiting the incremental CANDECOMP/PARAFCAC (CP) tensor decomposition algorithm. Then, to reduce the cumulative error by incremental prediction, we propose three strategies to restart the CP decomposition. To the best of our knowledge, this is the first work that identifies and solves the problem of incremental group-level popularity prediction. Extensive experimental results show significant improvements of the IGPP method over other works both in the prediction accuracy and the efficiency.

A Unified Perspective for Disinformation Detection and Truth Discovery in Social Sensing: A Survey

With the proliferation of social sensing, large amounts of observation are contributed by people or devices. However, these observations contain disinformation. Disinformation can propagate across online social networks at a relatively low cost, but result in a series of major problems in our society. In this survey, we provide a comprehensive overview of disinformation and truth discovery in social sensing under a unified perspective, including basic concepts and the taxonomy of existing methodologies. Furthermore, we summarize the mechanism of disinformation from four different perspectives (i.e., text only, text with image/multi-modal, text with propagation, and fusion models). In addition, we review existing solutions based on these requirements and compare their pros and cons and give a sort of guide to usage based on a detailed lesson learned. To facilitate future studies in this field, we summarize related publicly accessible real-world data sets and open source codes. Last but the most important, we emphasize potential future research topics and challenges in this domain through a deep analysis of most recent methods.

Exploiting Group Information for Personalized Recommendation with Graph Neural Networks

Personalized recommendation has become more and more important for users to quickly find relevant items. The key issue of the recommender system is how to model user preferences. Previous work mostly employed user historical data to learn users’ preferences, but faced with the data sparsity problem. The prevalence of online social networks promotes increasing online discussion groups, and users in the same group often have similar interests and preferences. Therefore, it is necessary to integrate group information for personalized recommendation. The existing work on group-information-enhanced recommender systems mainly relies on the item information related to the group, which is not expressive enough to capture the complicated preference dependency relationships between group users and the target user. In this article, we solve the problem with the graph neural networks. Specifically, the relationship between users and items, the item preferences of groups, and the groups that users participate in are constructed as bipartite graphs, respectively, and the user preferences for items are learned end to end through the graph neural network. The experimental results on the Last.fm and Douban Movie datasets show that considering group preferences can improve the recommendation performance and demonstrate the superiority on sparse users compared

Sentiment Analysis using Optimized Feature Sets in Different Facebook/Twitter Dataset Domains using Big Data

Now days, in many real life applications, the sentiment analysis plays very vital role for automatic prediction of human being activities especially on online social networks (OSNs). Therefore since from last decade, the research on opinion mining and sentiment analysis is growing with increasing volume of online reviews available over the social media networks like Facebook OSNs. Sentiment analysis falls under the data mining domain research problem. Sentiment analysis is kind of text mining process used to determine the subjective attitude like sentiment from the written texts and hence becoming the main research interest in domain of natural language processing and data mining. The main task in sentiment analysis is classifying human sentiment with objective of classifying the sentiment or emotion of end users for their specific text on OSNs. There are number of research methods designed already for sentiment analysis. There are many factors like accuracy, efficiency, speed etc. used to evaluate the effectiveness of sentiment analysis methods. The MapReduce framework under the domain of big-data is used to minimize the speed of execution and efficiency recently with many data mining methods. The sentiment analysis for Facebook OSNs messages is very challenging tasks as compared to other sentiment analysis because of misspellings and slang words presence in twitter dataset. In this paper, different solutions recently presented are discussed in detail. Then proposed the new approach for sentiment analysis based on hybrid features extraction methods and multi-class Support Vector Machine (SVM). These algorithms are designed using the Big-data techniques to optimize the performance of sentiment analysis

An explainable assistant for multiuser privacy

Multiuser Privacy (MP) concerns the protection of personal information in situations where such information is co-owned by multiple users. MP is particularly problematic in collaborative platforms such as online social networks (OSN). In fact, too often OSN users experience privacy violations due to conflicts generated by other users sharing content that involves them without their permission. Previous studies show that in most cases MP conflicts could be avoided, and are mainly due to the difficulty for the uploader to select appropriate sharing policies. For this reason, we present ELVIRA, the first fully explainable personal assistant that collaborates with other ELVIRA agents to identify the optimal sharing policy for a collectively owned content. An extensive evaluation of this agent through software simulations and two user studies suggests that ELVIRA, thanks to its properties of being role-agnostic, adaptive, explainable and both utility- and value-driven, would be more successful at supporting MP than other approaches presented in the literature in terms of (i) trade-off between generated utility and promotion of moral values, and (ii) users’ satisfaction of the explained recommended output.

What Accounts for the Variation in COVID-19 Vaccine Hesitancy in Eastern, Southern and Western Europe?

Attitudes towards vaccination have proven to be a major factor determining the pace of national COVID-19 vaccination campaigns throughout 2021. In Europe, large differences in levels of vaccine hesitancy and refusal have emerged, which are highly correlated with actual vaccination levels. This article explores attitudes towards COVID-19 vaccination in 27 European countries based on data from Eurobarometer (May 2021). The statistical analyses show that demographic variables have complex effects on vaccine hesitancy and refusal. Trust in different sources of health-related information has significant effects as well, with people who trust the Internet, social networks and ‘people around’ in particular being much more likely to express vaccine skepticism. As expected, beliefs in the safety and effectiveness of vaccines have large predictive power, but – more interestingly – net of these two beliefs, the effects of trust in Internet, online social networks and people as sources of health information are significantly reduced. This study shows that the effects of demographic, belief-related and other individual-level factors on vaccine hesitancy and refusal are context-specific. Yet, explanations of the differences in vaccine hesitancy across Europe need to consider primarily different levels of trust and vaccine-relevant beliefs, and to a lesser extent their differential effects.

A Novel Approach to the Measurement of Bourdieusian Social Capital within Institutional Pages and Profiles

We present in this paper a novel approach for measuring Bourdieusian Social Capital (BSC) within Institutional Pages and Profiles. We analyse Facebook's Institutional Pages and Twitter's Institutional Profiles. Supported by Pierre Bourdie's theory, we search for directions to identify and capture data related to sociability practices, i. e. actions performed such as Like, Comment and Share. The system of symbolic exchanges and mutual recognition treated by Pierre Bourdieu is represented and extracted automatically from these data in the form of generalized sequential patterns. In this format, the social interactions captured from each page are represented as sequences of actions. Next, we also use such data to measure the frequency of occurrence of each sequence. From such frequencies, we compute the effective mobilization capacity. Finally, the volume of BSC is computed based on the capacity of effective mobilization, the number of social interactions captured and the number of followers on each page. The results are aligned with Bourdieu's theory. The approach can be generalized to institutional pages or profiles in Online Social Networks.