Over the last couple of decades in the lending industry, financial disintermediation has occurred on a global scale. Traditionally, even for small supply of funds, banks would act as the conduit between the funds and the borrowers. It has now been possible to overcome some of the obstacles associated with such supply of funds with the advent of online platforms like Kiva, Prosper, LendingClub. Kiva for example, works with Micro Finance Institutions (MFIs) in developing countries to build Internet profiles of borrowers with a brief biography, loan requested, loan term, and purpose. Kiva, in particular, allows lenders to fund projects in different sectors through group or individual funding. Traditional research studies have investigated various factors behind lender preferences purely from the perspective of loan attributes and only until recently have some cross-country cultural preferences been investigated. In this paper, we investigate lender perceptions of economic factors of the borrower countries in relation to their preferences towards loans associated with different sectors. We find that the influence from economic factors and loan attributes can have substantially different roles to play for different sectors in achieving faster funding. We formally investigate and quantify the hidden biases prevalent in different loan sectors using recent tools from causal inference and regression models that rely on Bayesian variable selection methods. We then extend these models to incorporate fairness constraints based on our empirical analysis and find that such models can still achieve near comparable results with respect to baseline regression models.

Over the past few years, we have observed different media outlets' attempts to shift public opinion by framing information to support a narrative that facilitate their goals. Malicious users referred to as "pathogenic social media" (PSM) accounts are more likely to amplify this phenomena by spreading misinformation to viral proportions. Understanding the spread of misinformation from account-level perspective is thus a pressing problem. In this work, we aim to present a feature-driven approach to detect PSM accounts in social media. Inspired by the literature, we set out to assess PSMs from three broad perspectives: (1) user-related information (e.g., user activity, profile characteristics), (2) source-related information (i.e., information linked via URLs shared by users) and (3) content-related information (e.g., tweets characteristics). For the user-related information, we investigate malicious signals using causality analysis (i.e., if user is frequently a cause of viral cascades) and profile characteristics (e.g., number of followers, etc.). For the source-related information, we explore various malicious properties linked to URLs (e.g., URL address, content of the associated website, etc.). Finally, for the content-related information, we examine attributes (e.g., number of hashtags, suspicious hashtags, etc.) from tweets posted by users. Experiments on real-world Twitter data from different countries demonstrate the effectiveness of the proposed approach in identifying PSM users.

Pathogenic Social Media (PSM) accounts such as terrorist supporters exploit large communities of supporters for conducting attacks on social media. Early detection of these accounts is crucial as they are high likely to be key users in making a harmful message "viral". In this paper, we make the first attempt on utilizing causal inference to identify PSMs within a short time frame around their activity. We propose a time-decay causality metric and incorporate it into a causal community detection-based algorithm. The proposed algorithm is applied to groups of accounts sharing similar causality features and is followed by a classification algorithm to classify accounts as PSM or not. Unlike existing techniques that take significant time to collect information such as network, cascade path, or content, our scheme relies solely on action log of users. Results on a real-world dataset from Twitter demonstrate effectiveness and efficiency of our approach. We achieved precision of 0.84 for detecting PSMs only based on their first 10 days of activity; the misclassified accounts were then detected 10 days later.

The spread of harmful mis-information in social media is a pressing problem. We refer accounts that have the capability of spreading such information to viral proportions as "Pathogenic Social Media" accounts. These accounts include terrorist supporters accounts, water armies, and fake news writers. We introduce an unsupervised causality-based framework that also leverages label propagation. This approach identifies these users without using network structure, cascade path information, content and user's information. We show our approach obtains higher precision (0.75) in identifying Pathogenic Social Media accounts in comparison with random (precision of 0.11) and existing bot detection (precision of 0.16) methods.

The lack of sufficient labeled examples for devising and training sophisticated approaches to combat PSM accounts is still one of the foremost challenges facing social media firms. In contrast, unlabeled data is abundant and cheap to obtain thanks to the massive user-generated data produced on a daily basis. This chapter proposes a semi-supervised causal inference PSM detection framework, SemiPsm, to compensate for the lack of labeled data for identifying PSM users. The proposed method leverages unlabeled data in the form of manifold regularization and only relies on cascade information from users’ activities. This is in contrast to the existing approaches that use exhaustive feature engineering (e.g., profile information, network structure, etc.). Evidence from empirical experiments on the ISIS-B dataset from previous chapters suggests promising results of utilizing unlabeled instances for detecting PSMs.

Over the past years, political events and public opinion on the Web have been allegedly manipulated by "Pathogenic Social Media (PSM)" accounts dedicated to spreading disinformation and performing malicious activities. These accounts are often controlled by terrorist supporters, water armies, or fake news writers and hence can pose threats to social media and general public. Understanding and analyzing PSMs could help social media devise sophisticated techniques to stop them from reaching their audience and consequently reduce their threat. In this chapter, probabilistic causal inference and well-known statistical technique Hawkes processes are utilized to distinguish between PSM and non-PSM accounts. Results on real-world ISIS-related datasets from Twitter demonstrate that PSMs behave significantly differently from regular users while disseminating information.

In this chapter, we adopt the causal inference framework described previously along with graph-based metrics to distinguish PSMs from normal users within a short time of their activities. We propose both supervised and semi-supervised approaches without taking the network information and content into account. Results on the ISIS-A dataset demonstrate the advantage of our proposed frameworks. We show our approach achieves 0.28 improvement in F1 score over existing approaches with the precision of 0.90 and F1 score of 0.63.

Recommendation is one of the critical applications that helps users find information relevant to their interests. However, a malicious attacker can infer users' private information via recommendations. Prior work obfuscates user-item data before sharing it with recommendation system. This approach does not explicitly address the quality of recommendation while performing data obfuscation. Moreover, it cannot protect users against private-attribute inference attacks based on recommendations. This work is the first attempt to build a Recommendation with Attribute Protection (RAP) model which simultaneously recommends relevant items and counters private-attribute inference attacks. The key idea of our approach is to formulate this problem as an adversarial learning problem with two main components: the private attribute inference attacker, and the Bayesian personalized recommender. The attacker seeks to infer users' private-attribute information according to their items list and recommendations. The recommender aims to extract users' interests while employing the attacker to regularize the recommendation process. Experiments show that the proposed model both preserves the quality of recommendation service and protects users against private-attribute inference attacks.

The ease of use of the Internet has enabled violent extremists such as the Islamic State of Iraq and Syria (ISIS) to easily reach large audience, build personal relationships and increase recruitment. Social media are primarily based on the reports they receive from their own users to mitigate the problem. Despite efforts of social media in suspending many accounts, this solution is not guaranteed to be effective, because not all extremists are caught this way, or they can simply return with another account or migrate to other social networks. In this paper, we design an automatic detection scheme that using as little as three groups of information related to usernames, profile, and textual content of users, determines whether or not a given username belongs to an extremist user. We first demonstrate that extremists are inclined to adopt usernames that are similar to the ones that their like-minded have adopted in the past. We then propose a detection framework that deploys features which are highly indicative of potential online extremism. Results on a real-world ISIS-related dataset from Twitter demonstrate the effectiveness of the methodology in identifying extremist users.

Over the past years, political events and public opinion on the Web have been allegedly manipulated by accounts dedicated to spreading disinformation and performing malicious activities on social media. These accounts hereafter referred to as 'Pathogenic Social Media (PSM)" accounts, are often controlled by terrorist supporters, water armies or fake news writers and hence can pose threats to social media and general public. Understanding and analyzing PSMs could help social media firms devise sophisticated and automated techniques that could be deployed to stop them from reaching their audience and consequently reduce their threat. In this paper, we leverage the well-known statistical technique "Hawkes Process" to quantify the influence of PSM accounts on the dissemination of malicious information on social media platforms. Our findings on a real world ISIS -related dataset from Twitter indicate that PSMs are significantly different from regular users in making a message viral. Specifically, we observed that PSMs do not usually post URLs from mainstream news sources. Instead, their tweets usually receive large impact on audience, if contained URLs from Facebook and alternative news outlets. In contrary, tweets posted by regular users receive nearly equal impression regardless of the posted URLs and their sources. Our findings can further shed light on understanding and detecting PSM accounts.

Information diffusion mechanisms based on social influence models are mainly studied using likelihood of adoption when active neighbors expose a user to a message. The problem arises primarily from the fact that for the most part, this explicit information of who-exposed-whom among a group of active neighbors in a social network, before a susceptible node is infected is not available. In this paper, we attempt to understand the diffusion process through information cascades by studying the temporal network structure of the cascades. In doing so, we accommodate the effect of exposures from active neighbors of a node through a network pruning technique that leverages network motifs to identify potential infectors responsible for exposures from among those active neighbors. We attempt to evaluate the effectiveness of the components used in modeling cascade dynamics and especially whether the additional effect of the exposure information is useful. Following this model, we develop an inference algorithm namely InferCut, that uses parameters learned from the model and the exposure information to predict the actual parent node of each potentially susceptible user in a given cascade. Empirical evaluation on a real world dataset from Weibo social network demonstrate the significance of incorporating exposure information in recovering the exact parents of the exposed users at the early stages of the diffusion process.

A growing set of applications consider the process of network formation by using subgraphs as a tool for generating the network topology. One of the pressing research challenges is thus to be able to use these subgraphs to understand the network topology of information cascades which ultimately paves the way to theorize about how information spreads over time. In this paper, we make the first attempt at using network motifs to understand whether or not they can be used as generative elements for the diffusion network organization during different phases of the cascade lifecycle. In doing so, we propose a motif percolation-based algorithm that uses network motifs to measure the extent to which they can represent the temporal cascade network organization. We compare two phases of the cascade lifecycle from the perspective of diffusion-- the phase of steep growth and the phase of inhibition prior to its saturation. Our experiments on a set of cascades from the Weibo platform and with 5-node motifs demonstrate that there are only a few specific motif patterns with triads that are able to characterize the spreading process and hence the network organization during the inhibition region better than during the phase of high growth. In contrast, we do not find compelling results for the phase of steep growth.

Pathogenic Social Media (PSM) accounts such as terrorist supporter accounts and fake news writers have the capability of spreading disinformation to viral proportions. Early detection of PSM accounts is crucial as they are likely to be key users to make malicious information "viral". In this paper, we adopt the causal inference framework along with graph-based metrics in order to distinguish PSMs from normal users within a short time of their activities. We propose both supervised and semi-supervised approaches without taking the network information and content into account. Results on a real-world dataset from Twitter accentuates the advantage of our proposed frameworks. We show our approach achieves 0.28 improvement in F1 score over existing approaches with the precision of 0.90 and F1 score of 0.63.

Recent years have witnessed a surge of manipulation of public opinion and political events by malicious social media actors. These users are referred to as Pathogenic Social Media (PSM) accounts. PSMs are key users in spreading misinformation in social media to viral proportions. These accounts can be either controlled by real users or automated bots. Identification of PSMs is thus of utmost importance for social media authorities. The burden usually falls to automatic approaches that can identify these accounts and protect social media reputation. However, lack of sufficient labeled examples for devising and training sophisticated approaches to combat these accounts is still one of the foremost challenges facing social media firms. In contrast, unlabeled data is abundant and cheap to obtain thanks to massive user-generated data. In this paper, we propose a semi-supervised causal inference PSM detection framework, SemiPsm, to compensate for the lack of labeled data. In particular, the proposed method leverages unlabeled data in the form of manifold regularization and only relies on cascade information. This is in contrast to the existing approaches that use exhaustive feature engineering (e.g., profile information, network structure, etc.). Evidence from empirical experiments on a real-world ISIS-related dataset from Twitter suggests promising results of utilizing unlabeled instances for detecting PSMs.

Twitter, one of the biggest and most popular microblogging Websites, has evolved into a powerful communication platform which allows millions of active users to generate huge volume of microposts and queries on a daily basis. To accommodate effective categorization and easy search, users are allowed to make use of hashtags, keywords or phrases prefixed by hash character, to categorize and summarize their posts. However, valid hashtags are not restricted and thus are created in a free and heterogeneous style, increasing difficulty of the task of tweet categorization. In this paper, we propose a low-rank weighted matrix factorization based method to recommend hashtags to the users solely based on their hashtag usage history and independent from their tweets' contents. We confirm using two-sample t-test that users are more likely to adopt new hashtags similar to the ones they have previously adopted. In particular, we formulate the problem of hashtag recommendation into an optimization problem and incorporate hashtag correlation weight matrix into it to account for the similarity between different hashtags. We finally leverage widely used matrix factorization from recommender systems to solve the optimization problem by capturing the latent factors of users and hashtags. Empirical experiments demonstrate that our method is capable to properly recommend hashtags.

High-order parametric models that include terms for feature interactions are applied to various data mining tasks, where ground truth depends on interactions of features. However, with sparse data, the high-dimensional parameters for feature interactions often face three issues: expensive computation, difficulty in parameter estimation and lack of structure. Previous work has proposed approaches which can partially resolve the three issues. In particular, models with factorized parameters (e.g. Factorization Machines) and sparse learning algorithms (e.g. FTRL-Proximal) can tackle the first two issues but fail to address the third. Regarding to unstructured parameters, constraints or complicated regularization terms are applied such that hierarchical structures can be imposed. However, these methods make the optimization problem more challenging. In this work, we propose Strongly Hierarchical Factorization Machines and ANOVA kernel regression where all the three issues can be addressed without making the optimization problem more difficult. Experimental results show the proposed models significantly outperform the state-of-the-art in two data mining tasks: cold-start user response time prediction and stock volatility prediction.