arXiv subjects

Pádraig Cunningham

Publications and source records attributed to Pádraig Cunningham.

31 records · Page 2Linked to original sources

arXiv2013

The Extreme Right Filter Bubble

Due to its status as the most popular video sharing platform, YouTube plays an important role in the online strategy of extreme right groups, where it is often used to host associated content such as music and other propaganda. In this paper, we develop a categorization suitable for the analysis of extreme right channels found on YouTube. By combining this with an NMF-based topic modelling method, we categorize channels originating from links propagated by extreme right Twitter accounts. This method is also used to categorize related channels, which are determined using results returned by YouTube's related video service. We identify the existence of a "filter bubble", whereby users who access an extreme right YouTube video are highly likely to be recommended further extreme right content.

cs.SI↗

arXiv2013

Discovering Latent Patterns from the Analysis of User-Curated Movie Lists

User content curation is becoming an important source of preference data, as well as providing information regarding the items being curated. One popular approach involves the creation of lists. On Twitter, these lists might contain accounts relevant to a particular topic, whereas on a community site such as the Internet Movie Database (IMDb), this might take the form of lists of movies sharing common characteristics. While list curation involves substantial combined effort on the part of users, researchers have rarely looked at mining the outputs of this kind of crowdsourcing activity. Here we study a large collection of movie lists from IMDb. We apply network analysis methods to a graph that reflects the degree to which pairs of movies are "co-listed", that is, assigned to the same lists. This allows us to uncover a more nuanced grouping of movies that goes beyond categorisation schemes based on attributes such as genre or director.

cs.SI↗

arXiv2013

TwitterCrowds: Techniques for Exploring Topic and Sentiment in Microblogging Data

Analysts and social scientists in the humanities and industry require techniques to help visualize large quantities of microblogging data. Methods for the automated analysis of large scale social media data (on the order of tens of millions of tweets) are widely available, but few visualization techniques exist to support interactive exploration of the results. In this paper, we present extended descriptions of ThemeCrowds and SentireCrowds, two tag-based visualization techniques for this data. We subsequently introduce a new list equivalent for both of these techniques and present a number of case studies showing them in operation. Finally, we present a formal user study to evaluate the effectiveness of these list interface equivalents when comparing them to ThemeCrowds and SentireCrowds. We find that discovering topics associated with areas of strong positive or negative sentiment is faster when using a list interface. In terms of user preference, multilevel tag clouds were found to be more enjoyable to use. Despite both interfaces being usable for all tested tasks, we have evidence to support that list interfaces can be more efficient for tasks when an appropriate ordering is known beforehand.

cs.SI↗

arXiv2013

Uncovering the Wider Structure of Extreme Right Communities Spanning Popular Online Networks

Recent years have seen increased interest in the online presence of extreme right groups. Although originally composed of dedicated websites, the online extreme right milieu now spans multiple networks, including popular social media platforms such as Twitter, Facebook and YouTube. Ideally therefore, any contemporary analysis of online extreme right activity requires the consideration of multiple data sources, rather than being restricted to a single platform. We investigate the potential for Twitter to act as a gateway to communities within the wider online network of the extreme right, given its facility for the dissemination of content. A strategy for representing heterogeneous network data with a single homogeneous network for the purpose of community detection is presented, where these inherently dynamic communities are tracked over time. We use this strategy to discover and analyze persistent English and German language extreme right communities.

cs.SI↗

arXiv2013

Link Prediction with Social Vector Clocks

State-of-the-art link prediction utilizes combinations of complex features derived from network panel data. We here show that computationally less expensive features can achieve the same performance in the common scenario in which the data is available as a sequence of interactions. Our features are based on social vector clocks, an adaptation of the vector-clock concept introduced in distributed computing to social interaction networks. In fact, our experiments suggest that by taking into account the order and spacing of interactions, social vector clocks exploit different aspects of link formation so that their combination with previous approaches yields the most accurate predictor to date.

cs.SI↗

arXiv2013

Producing a Unified Graph Representation from Multiple Social Network Views

In many social networks, several different link relations will exist between the same set of users. Additionally, attribute or textual information will be associated with those users, such as demographic details or user-generated content. For many data analysis tasks, such as community finding and data visualisation, the provision of multiple heterogeneous types of user data makes the analysis process more complex. We propose an unsupervised method for integrating multiple data views to produce a single unified graph representation, based on the combination of the k-nearest neighbour sets for users derived from each view. These views can be either relation-based or feature-based. The proposed method is evaluated on a number of annotated multi-view Twitter datasets, where it is shown to support the discovery of the underlying community structure in the data.

cs.SI↗

arXiv2013

Benchmarking community detection methods on social media data

Benchmarking the performance of community detection methods on empirical social network data has been identified as critical for improving these methods. In particular, while most current research focuses on detecting communities in data that has been digitally extracted from large social media and telecommunications services, most evaluation of this research is based on small, hand-curated datasets. We argue that these two types of networks differ so significantly that by evaluating algorithms solely on the former, we know little about how well they perform on the latter. To address this problem, we consider the difficulties that arise in constructing benchmarks based on digitally extracted network data, and propose a task-based strategy which we feel addresses these difficulties. To demonstrate that our scheme is effective, we use it to carry out a substantial benchmark based on Facebook data. The benchmark reveals that some of the most popular algorithms fail to detect fine-grained community structure.

cs.SI↗

arXiv2013

Measuring the Significance of the Geographic Flow of Music

In previous work, our results suggested that some cities tend to be ahead of others in their musical preferences. We concluded that work by noting that to properly test this claim, we would try to exploit the leader-follower relationships that we identified to make predictions. Here we present the results of our predictive evaluation. We find that information on the past musical preferences in other cities allows a linear model to improve its predictions by approx. 5% over a simple baseline. This suggests that at best, previously found leader-follower relationships are rather weak.

cs.SI↗

arXiv2012

Aggregating Content and Network Information to Curate Twitter User Lists

Twitter introduced user lists in late 2009, allowing users to be grouped according to meaningful topics or themes. Lists have since been adopted by media outlets as a means of organising content around news stories. Thus the curation of these lists is important - they should contain the key information gatekeepers and present a balanced perspective on a story. Here we address this list curation process from a recommender systems perspective. We propose a variety of criteria for generating user list recommendations, based on content analysis, network analysis, and the "crowdsourcing" of existing user lists. We demonstrate that these types of criteria are often only successful for datasets with certain characteristics. To resolve this issue, we propose the aggregation of these different "views" of a news story on Twitter to produce more accurate user recommendations to support the curation process.

cs.SI↗

arXiv2012

Identifying Topical Twitter Communities via User List Aggregation

A particular challenge in the area of social media analysis is how to find communities within a larger network of social interactions. Here a community may be a group of microblogging users who post content on a coherent topic, or who are associated with a specific event or news story. Twitter provides the ability to curate users into lists, corresponding to meaningful topics or themes. Here we describe an approach for crowdsourcing the list building efforts of many different Twitter users, in order to identify topical communities. This approach involves the use of ensemble community finding to produce stable groupings of user lists, and by extension, individual Twitter users. We examine this approach in the context of a case study surrounding the detection of communities on Twitter relating to the London 2012 Olympics.

cs.SI↗

arXiv2012

The Geographic Flow of Music

The social media website last.fm provides a detailed snapshot of what its users in hundreds of cities listen to each week. After suitably normalizing this data, we use it to test three hypotheses related to the geographic flow of music. The first is that although many of the most popular artists are listened to around the world, music preferences are closely related to nationality, language, and geographic location. We find support for this hypothesis, with a couple of minor, yet interesting, exceptions. Our second hypothesis is that some cities are consistently early adopters of new music (and early to snub stale music). To test this hypothesis, we adapt a method previously used to detect the leadership networks present in flocks of birds. We find empirical support for the claim that a similar leadership network exists among cities, and this finding is the main contribution of the paper. Finally, we test the hypothesis that large cities tend to be ahead of smaller cities-we find only weak support for this hypothesis.

cs.SI↗

arXiv2012

Identifying Discriminating Network Motifs in YouTube Spam

Like other social media websites, YouTube is not immune from the attention of spammers. In particular, evidence can be found of attempts to attract users to malicious third-party websites. As this type of spam is often associated with orchestrated campaigns, it has a discernible network signature, based on networks derived from comments posted by users to videos. In this paper, we examine examples of different YouTube spam campaigns of this nature, and use a feature selection process to identify network motifs that are characteristic of the corresponding campaign strategies. We demonstrate how these discriminating motifs can be used as part of a network motif profiling process that tracks the activity of spam user accounts over time, enabling the process to scale to larger networks.

cs.SI↗

arXiv2012

Network Analysis of Recurring YouTube Spam Campaigns

As the popularity of content sharing websites such as YouTube and Flickr has increased, they have become targets for spam, phishing and the distribution of malware. On YouTube, the facility for users to post comments can be used by spam campaigns to direct unsuspecting users to bogus e-commerce websites. In this paper, we demonstrate how such campaigns can be tracked over time using network motif profiling, i.e. by tracking counts of indicative network motifs. By considering all motifs of up to five nodes, we identify discriminating motifs that reveal two distinctly different spam campaign strategies. One of these strategies uses a small number of spam user accounts to comment on a large number of videos, whereas a larger number of accounts is used with the other. We present an evaluation that uses motif profiling to track two active campaigns matching these strategies, and identify some of the associated user accounts.

cs.SI↗