Role-Aware Information Spread in Online Social Networks

Understanding the complex process of information spread in online social networks (OSNs) enables the efficient maximization/minimization of the spread of useful/harmful information. Users assume various roles based on their behaviors while engaging with information in these OSNs. Recent reviews on information spread in OSNs have focused on algorithms and challenges for modeling the local node-to-node cascading paths of viral information. However, they neglected to analyze non-viral information with low reach size that can also spread globally beyond OSN edges (links) via non-neighbors through, for example, pushed information via content recommendation algorithms. Previous reviews have also not fully considered user roles in the spread of information. To address these gaps, we: (i) provide a comprehensive survey of the latest studies on role-aware information spread in OSNs, also addressing the different temporal spreading patterns of viral and non-viral information; (ii) survey modeling approaches that consider structural, non-structural, and hybrid features, and provide a taxonomy of these approaches; (iii) review software platforms for the analysis and visualization of role-aware information spread in OSNs; and (iv) describe how information spread models enable useful applications in OSNs such as detecting influential users. We conclude by highlighting future research directions for studying information spread in OSNs, accounting for dynamic user roles.

Equality of Learning Opportunity via Individual Fairness in Personalized Recommendations

Online education platforms play an increasingly important role in mediating the success of individuals’ careers. Therefore, while building overlying content recommendation services, it becomes essential to guarantee that learners are provided with equal recommended learning opportunities, according to the platform principles, context, and pedagogy. Though the importance of ensuring equality of learning opportunities has been well investigated in traditional institutions, how this equality can be operationalized in online learning ecosystems through recommender systems is still under-explored. In this paper, we shape a blueprint of the decisions and processes to be considered in the context of equality of recommended learning opportunities, based on principles that need to be empirically-validated (no evaluation with live learners has been performed). To this end, we first provide a formalization of educational principles that model recommendations’ learning properties, and a novel fairness metric that combines them to monitor the equality of recommended learning opportunities among learners. Then, we envision a scenario wherein an educational platform should be arranged in such a way that the generated recommendations meet each principle to a certain degree for all learners, constrained to their individual preferences. Under this view, we explore the learning opportunities provided by recommender systems in a course platform, uncovering systematic inequalities. To reduce this effect, we propose a novel post-processing approach that balances personalization and equality of recommended opportunities. Experiments show that our approach leads to higher equality, with a negligible loss in personalization. This paper provides a theoretical foundation for future studies of learners’ preferences and limits concerning the equality of recommended learning opportunities.

Indirect causal influence of a single bot on opinion dynamics through a simple recommendation algorithm

The ability of social and political bots to influence public opinion is often difficult to estimate. Recent studies found that hyper-partisan accounts often directly interact with already highly polarised users on Twitter and are unlikely to influence the general population's average opinion. In this study, we suggest that social bots, trolls and zealots may affect people’s views not just via a direct interaction (e.g. retweets, at-mentions and likes) and via indirect causal pathways through infiltrating platforms’ content recommendation systems. Using a simple agent-based opinion-dynamics simulation, we isolate the effect of a single bot – representing only 1% of the population – on the average opinion of Bayesian agents when we remove all direct connections between the bot and human agents. We compare this experimental condition with an identical baseline condition where such a bot is absent. We used the same random seed in both simulations so that all other conditions remained identical. Results show that, even in the absence of direct connections, the presence of the bot is sufficient to shift the average population opinion. Furthermore, we observe that the presence of the bot significantly affects the opinion of almost all agents in the population. Overall, these findings indicate that social bots and hyperpartisan accounts can influence average population opinions by changing platforms’ recommendation engines’ internal representations.

Popularity Prediction of Online Contents via Cascade Graph and Temporal Information

Predicting the popularity of online content is an important task for content recommendation, social influence prediction and so on. Recent deep learning models generally utilize graph neural networks to model the complex relationship between information cascade graph and future popularity, and have shown better prediction results compared with traditional methods. However, existing models adopt simple graph pooling strategies, e.g., summation or average, which prone to generate inefficient cascade graph representation and lead to unsatisfactory prediction results. Meanwhile, they often overlook the temporal information in the diffusion process which has been proved to be a salient predictor for popularity prediction. To focus attention on the important users and exclude noises caused by other less relevant users when generating cascade graph representation, we learn the importance coefficient of users and adopt sample mechanism in graph pooling process. In order to capture the temporal features in the diffusion process, we incorporate the inter-infection duration time information into our model by using LSTM neural network. The results show that temporal information rather than cascade graph information is a better predictor for popularity. The experimental results on real datasets show that our model significantly improves the prediction accuracy compared with other state-of-the-art methods.

Ethical and legal implications of using AI-powered recommendation systems in streaming services

Recommendation engines are commonly used in the entertainment industry to keep users glued in front of their screens. These engines are becoming increasingly sophisticated as machine learning tools are being built into ever-more complex AI-driven systems that enable providers to effectively map user preferences. The utilization of AI-powered tools, however, has serious ethical and legal implications. Some of the emerging issues are already being addressed by ethical codes, developed by international organizations and supranational bodies. The present study aimed to address the key challenges posed by AI-powered content recommendation engines. Consequently, this paper introduces the relevant rules present in the existing ethical guidelines and elaborates on how they are to be applied within the streaming industry. The paper strives to adopt a critical standpoint towards the provisions of the ethical guidelines in place, arguing that adopting a one-size-fits all approach is not effective due to the specificities of the content distribution industry.

Classification of Tweets for Video Streaming Services’ Content Recommendation on Twitter

<p>Streaming services were popular platforms often visited by internet users. However, the abundance of content can be confusing for its users, prompting them to look for a recommendation from other people. Some of the users looked for content to enjoy with the help of Twitter. However, there were irrelevant tweets shown in the results, showing sentences not related at all to the content in the streaming services platform. This study addressed the classification of relevant and irrelevant tweets for streaming services’ content recommendation using random forests and the Convolutional Neural Network (CNN). The result showed that the CNN performed better in the test set with higher accuracy of 94% but slower in running time compared to the random forest. There were indeed distinctive characteristics between the two categories of the tweets. Finally, based on the resulting classification, users could identify the right words to use and avoid while searching on Twitter.</p><strong>Keywords: </strong>text mining, streaming services, classification, random forest, CNN

Content Recommendation on Small Scale Sparse Social Network

Small scale social network platforms suffer from increased sparsity, both in the size of text posted by users and the number of posts, as well as the specific nature of kurtosis that affects all platforms, yet more so on an emerging platform. In this work we examine a dataset from such a platform, where the majority of the activity is in the form of user generated text; both posted content and comments left on those posts. We inquire into what techniques would present suitable recommendations for a platform with a similar characteristic dataset. We evaluate leading textual analysis techniques and show how topic-model based techniques present a viable means for recommendation on such a platform as compared to other simpler, or more advanced techniques.

Content Recommendation on Small Scale Sparse Social Network

Small scale social network platforms suffer from increased sparsity, both in the size of text posted by users and the number of posts, as well as the specific nature of kurtosis that affects all platforms, yet more so on an emerging platform. In this work we examine a dataset from such a platform, where the majority of the activity is in the form of user generated text; both posted content and comments left on those posts. We inquire into what techniques would present suitable recommendations for a platform with a similar characteristic dataset. We evaluate leading textual analysis techniques and show how topic-model based techniques present a viable means for recommendation on such a platform as compared to other simpler, or more advanced techniques.