Data Mining - Concepts and Techniques.

http://cfile28.uf.tistory.com/attach/23159E3D57117DF7107077

Twitter mood predicts the stock market.

Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many security-sensitive applications like payment apps. Such usages of deep learning systems provide the adversaries with sufficient incentives to perform attacks against these systems for their adversarial purposes. In this work, we consider a new type of attacks, called backdoor attacks, where the attacker's goal is to create a backdoor into a learning-based authentication system, so that he can easily circumvent the system by leveraging the backdoor. Specifically, the adversary aims at creating backdoor instances, so that the victim learning system will be misled to classify the backdoor instances as a target label specified by the adversary. In particular, we study backdoor poisoning attacks, which achieve backdoor attacks using poisoning strategies. Different from all existing work, our studied poisoning strategies can apply under a very weak threat model: (1) the adversary has no knowledge of the model and the training set used by the victim system; (2) the attacker is allowed to inject only a small amount of poisoning samples; (3) the backdoor key is hard to notice even by human beings to achieve stealthiness. We conduct evaluation to demonstrate that a backdoor adversary can inject only around 50 poisoning samples, while achieving an attack success rate of above 90%. We are also the first work to show that a data poisoning attack can create physically implementable backdoors without touching the training process. Our work demonstrates that backdoor poisoning attacks pose real threats to a learning system, and thus highlights the importance of further investigation and proposing defense strategies against them.

Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning

Sentiment analysis is concerned with the automatic extraction of sentiment-related information from text. Although most sentiment analysis addresses commercial tasks, such as extracting opinions from product reviews, there is increasing interest in the affective dimension of the social web, and Twitter in particular. Most sentiment analysis algorithms are not ideally suited to this task because they exploit indirect indicators of sentiment that can reflect genre or topic instead. Hence, such algorithms used to process social web texts can identify spurious sentiment patterns caused by topics rather than affective phenomena. This article assesses an improved version of the algorithm SentiStrength for sentiment strength detection across the social web that primarily uses direct indications of sentiment. The results from six diverse social web data sets (MySpace, Twitter, YouTube, Digg, RunnersWorld, BBCForums) indicate that SentiStrength 2 is successful in the sense of performing better than a baseline approach for all data sets in both supervised and unsupervised cases. SentiStrength is not always better than machine-learning approaches that exploit indirect indicators of sentiment, however, and is particularly weaker for positive sentiment in news-related discussions. Overall, the results suggest that, even unsupervised, SentiStrength is robust enough to be applied to a wide variety of different social web contexts.

/pdf/sentiment-strength-detection-for-the-social-web-3reirisoz3.pdf

Sentiment strength detection for the social web

Individual happiness is a fundamental societal metric. Normally measured through self-report, happiness has often been indirectly characterized and overshadowed by more readily quantifiable economic indicators such as gross domestic product. Here, we examine expressions made on the online, global microblog and social networking service Twitter, uncovering and explaining temporal variations in happiness and information levels over timescales ranging from hours to years. Our data set comprises over 46 billion words contained in nearly 4.6 billion expressions posted over a 33 month span by over 63 million unique users. In measuring happiness, we construct a tunable, real-time, remote-sensing, and non-invasive, text-based hedonometer. In building our metric, made available with this paper, we conducted a survey to obtain happiness evaluations of over 10,000 individual words, representing a tenfold size improvement over similar existing word sets. Rather than being ad hoc, our word list is chosen solely by frequency of usage, and we show how a highly robust and tunable metric can be constructed and defended.

/pdf/temporal-patterns-of-happiness-and-information-in-a-global-3ggytipc51.pdf

Temporal Patterns of Happiness and Information in a Global Social Network: Hedonometrics and Twitter

Online social networking communities may exhibit highly complex and adaptive collective behaviors. Since emotions play such an important role in human decision making, how online networks modulate human collective mood states has become a matter of considerable interest. In spite of the increasing societal importance of online social networks, it is unknown whether assortative mixing of psychological states takes place in situations where social ties are mediated solely by online networking services in the absence of physical contact. Here, we show that the general happiness, or subjective well-being (SWB), of Twitter users, as measured from a 6-month record of their individual tweets, is indeed assortative across the Twitter social network. Our results imply that online social networks may be equally subject to the social mechanisms that cause assortative mixing in real social networks and that such assortative mixing takes place at the level of SWB. Given the increasing prevalence of online social networks, their propensity to connect users with similar levels of SWB may be an important factor in how positive and negative sentiments are maintained and spread through human society. Future research may focus on how event-specific mood states can propagate and influence user behavior in "real life."

/pdf/happiness-is-assortative-in-online-social-networks-41ck28ytq3.pdf

Happiness is assortative in online social networks

Most individuals in social networks experience a so-called Friendship Paradox: they are less popular than their friends on average. This effect may explain recent findings that widespread social network media use leads to reduced happiness. However the relation between popularity and happiness is poorly understood. A Friendship paradox does not necessarily imply a Happiness paradox where most individuals are less happy than their friends. Here we report the first direct observation of a significant Happiness Paradox in a large-scale online social network of 39,110 Twitter users. Our results reveal that popular individuals are indeed happier and that a majority of individuals experience a significant Happiness paradox. The magnitude of the latter effect is shaped by complex interactions between individual popularity, happiness, and the fact that users strongly cluster by similar level of happiness. Our results indicate that the topology of online social networks, combined with how happiness is distributed in some populations, may be associated with significant psycho-social effects.

/pdf/the-happiness-paradox-your-friends-are-happier-than-you-v2nld08mwr.pdf

The happiness paradox: your friends are happier than you

In this paper, a three-layer back-propagation neural network (BPNN) is employed for spam detection by using a concentration based feature construction (CFC) approach. In the CFC approach, `self' and `non-self' concentrations are constructed through `self' and `non-self' gene libraries, respectively, to form a two-element concentration vector for expressing the e-mail efficiently. A three-layer BPNN with two-element input is then employed to classify e-mails automatically. Comprehensive experiments are conducted on two public benchmark corpora PU1 and Ling to demonstrate that the proposed CFC approach based BPNN classifier not only has a very much fast speed but also achieves 97 and 99% of classification accuracy on corpora PU1 and Ling by just using a two-element concentration feature vector.

A three-layer back-propagation neural network for spam detection using artificial immune concentration

Most individuals in social networks experience a so-called Friendship Paradox: they are less popular than their friends on average. This effect may explain recent findings that widespread social network media use leads to reduced happiness. However the relation between popularity and happiness is poorly understood. A Friendship paradox does not necessarily imply a Happiness paradox where most individuals are less happy than their friends. Here we report the first direct observation of a significant Happiness Paradox in a large-scale online social network of $39,110$ Twitter users. Our results reveal that popular individuals are indeed happier and that a majority of individuals experience a significant Happiness paradox. The magnitude of the latter effect is shaped by complex interactions between individual popularity, happiness, and the fact that users cluster assortatively by level of happiness. Our results indicate that the topology of online social networks and the distribution of happiness in some populations can cause widespread psycho-social effects that affect the well-being of billions of individuals.

As digital data sources grow in number and size, they pose an opportunity for computational investigation by means of text mining, natural language processing (NLP), and other text analysis techniques. In this paper we propose a virtual machine (VM) framework and methodology for non-consumptive text analysis. Using a remote VM model, the VM is configured with software and tooling for text analysis. When completed, the VM is wiped out and resources released for other users to share. Our approach extends the VM by turning it into a data capsules that prevents leakage of copyrighted content in the event that the VM is compromised. The HathiTrust Research Center Data Capsules has seen early use in application against the HathiTrust repository of digitized books from university libraries nationwide.

/pdf/cloud-computing-data-capsules-for-non-consumptiveuse-of-4h6123gxuc.pdf

Guangchen Ruan

Papers

Happiness is assortative in online social networks

The happiness paradox: your friends are happier than you

A three-layer back-propagation neural network for spam detection using artificial immune concentration

The happiness paradox: your friends are happier than you

Cloud computing data capsules for non-consumptiveuse of texts