HCI Bibliography Home | HCI Conferences | SocialCom Archive | Detailed Records | RefWorks | EndNote | Hide Abstracts
SocialCom Tables of Contents: 14

Proceedings of the 2014 ASE International Conference on Social Computing

Fullname:Seventh ASE International Conference on Social Computing
Editors:Su Yang; Kristina Lerman; James She; Martin Atzmueller
Location:Beijing, China
Dates:2014-Aug-04 to 2014-Aug-07
Publisher:ACM
Standard No:ISBN: 978-1-4503-2888-3; ACM DL: Table of Contents; hcibib: SocialCom14
Papers:22
Links:Conference Website
  1. SocialCom Track 1: Social Networks, Media and Services
  2. SocialCom Track 2: Social Signal Processing
  3. Poster Abstracts
  4. 1st International Symposium on Recent Advances in Social Computing 2014

SocialCom Track 1: Social Networks, Media and Services

Optimisation of strategy placements for public good in complex networks BIBAFull-Text 1
  Dharshana Kasthurirathna; Harrison Nguyen; Mahendra Piraveenan; Shahadat Uddin; Upul Senanayake
Game theory has long been used to model cognitive decision making in societies. While traditional game theoretic modelling has focussed on well-mixed populations, recent research has suggested that the topological structure of social networks play an important part in the dynamic behaviour of social systems. Any agent or person playing a game employs a strategy (pure or mixed) to optimise pay-off. Previous studies have analysed how selfish agents can optimise their payoffs by choosing particular strategies within a social network model. In this paper we ask the question that, if agents were to work towards the common goal of increasing the public good (that is, the total network utility), what strategies they should adapt within the context of a heterogeneous network. We consider a number of classical and recently demonstrated game theoretic strategies, including cooperation, defection, general cooperation, Pavlov, and zero-determinant strategies, and compare them pairwise. We use the Iterative Prisoners Dilemma game simulated on scale-free networks, and use a genetic-algorithmic approach to investigate what optimal placement patterns evolve in terms of strategy. In particular, we ask the question that, given a pair of strategies are present in a network, which strategy should be adopted by the hubs (highly connected people), for the overall betterment of society (high network utility). We find that cooperation as opposed to defection, Pavlov as opposed to general cooperator, general cooperator as opposed to zero-determinant, and Pavlov as opposed to zero-determinant, strategies will be adopted by the hubs, for the overall increased utility of the network. The results are interesting, since given a scenario where certain individuals are only capable of implementing certain strategies, the results give a blueprint on where they should be placed in a complex network for the overall benefit of the society.
Enron Corporation: You're the Boss if People Get Mentioned to You BIBAFull-Text 2
  Apoorv Agarwal; Adinoyi Omuya; Jingwei Zhang; Owen Rambow
In this paper we use a new type of network, which we call the mention network, for the task of dominance prediction of employees of the Enron corporation given their emails. We show that the network formed using "who mentions whom to whom" links out-performs the traditionally used Enron email network. We present a comprehensive set of experiments to conclude that organizational dominance is best predicted by capturing the number of people mentioned to a person i.e. if many more people get mentioned to a person then that person is the boss.
Fairness-Aware Loan Recommendation for Microfinance Services BIBAFull-Text 3
  Eric L. Lee; Jing-Kai Lou; Wei-Ming Chen; Yen-Chi Chen; Shou-De Lin; Yen-Sheng Chiang; Kuan-Ta Chen
Up to date, more than 15 billion US dollars have been invested in microfinance that benefited more than 160 million people in developing countries. The Kiva organization is one of the successful examples that use a decentralized matching process to match lenders and borrowers. Interested lenders from around the world can look for cases among thousands of applicants they found promising to lend the money to. But how can loan borrowers and lenders be successfully matched up in a microfinance platform like Kiva? We argue that a sophisticate recommender not only pairs up loan lenders and borrowers in accordance to their preferences, but should also help to diversify the distribution of donations to reduce the inequality of loans is highly demanded, as altruism, like any resource, can be congestible.
   In this paper, we propose a fairness-aware recommendation system based on one-class collaborative-filtering techniques for charity and micro-loan platform such as Kiva.org. Our experiments on real dataset indicates that the proposed method can largely improve the loan distribution fairness while retaining the accuracy of recommendations.
Stimulating High Quality Social Media through Knowledge Barter-Auctioning BIBAFull-Text 4
  Qijin Ji; Haifeng Shen; Yuqing Mao; Yanqin Zhu
Incentives play a pivotal role in stimulating user-generated content (UGC), which is critical to the viability and success of today's social computing services. Non-financial social incentives are generally effective in boosting the quantity, but have limited effect on the quality. Conversely, financial incentives generally motivate better quality, but often complicate the efforts to attract quantity. In this paper, we propose knowledge barter-auctioning, a non-financial remunerative mechanism that is particularly effective in stimulating the quality of UGC yet without detriment to its quantity. This mechanism provides an optimal way for the knowledge vendor to choose the best barter partner in order to maximise their expected revenue, which is an extrinsic motivation for the triumph of quality as UGC of higher quality will enable the vendor to attract more bidders and consequently make a higher revenue through the barter auction. We have conducted a series of experiments using a real-world dataset to analyse the ramifications of UGC quality in knowledge bartering processes.
How to Become a More Popular Thread on Tianya Club BIBAFull-Text 5
  Jindong Chen; Lina Cao; Xijin Tang
In Bulletin Board System, when an author submits a post to start a thread, what kinds of elements affect the popularity of this thread? To address this issue, Tianya Zatan board of Tianya Club is selected as data source for this study. Through database and online data, the daily new threads with high degree of online interactions in 2012 are collected for analysis. To explore the key elements relating to the popularity of thread, several elements are analyzed using different methods: the topics of original posts are based on Latent Dirichlet Allocation, the high frequency words of titles, the basic features (the length of titles, the titles with/without the information of picture contained in the original posts, and the length of the content of original posts) and reply modes are based on statistics. Finally, several practical tips for an author to promote the popularity of the thread are given.
VANET-based Secure Value-Added Services BIBAFull-Text 6
  Shi-Jinn Horng; Shiang-Feng Tzeng
Due to the rapid development of the Internet, vehicular value-added services have become very prevalent in vehicular ad hoc network (VANET); especially for road safety and traffic management. In this paper, we propose a secure value-added service scheme based on blind signature technique for VANET. On one hand, the feature of the portable credential could eliminate the backend communications between roadside unit and service provider. Roadside unit could locally authenticate legitimate vehicles and make sure they are requesting their authorized services. On the other hand, vehicles could achieve the necessary privacy without revealing their real identities. Moreover, the proposed scheme provides more security features than previous works, especially in prevention of privilege elevation problem. Furthermore, compared to the results of those existing systems, we show that the proposed scheme is feasible and efficient.

SocialCom Track 2: Social Signal Processing

To Blog or Not to Blog: Characterizing and Predicting Retention in Community Blogs BIBAFull-Text 7
  Imrul Kayes; Xiang Zuo; Da Wang; Jacob Chakareski
Community blogging is a medium for publishing daily journals, expressing opinions or ideas, and sharing knowledge. Blogging has a high impact on marketing, shaping public opinions, and informing the world about major events from a grassroots point of view. However, turnover in online blogging is very high, with most people who initially join and start contributing to the community, failing to contribute in the long run.
   In this paper, we ask what factors cause a blogger to continue participating in the community by contributing content (e.g., posts, comments). We crawled a sample of blogger profiles from a popular community blogging platform "Blogster". These bloggers contributed about 91% posts in the community. We derived a set of well-grounded variables related to blogger retention and built a predictive model from the variables. Our results show that the male and aged (senior) bloggers, who face fewer constraints and have more opportunities in the community are more retained than others. Other bloggers pay a high degree of attention to these retained bloggers through implicit (reading posts) and explicit (writing comments) interactions.
   We have also found that a blogger has higher retention if her friends have also higher retention and a strong social tie reduces retention imbalance between two blogger friends. However, we found that a blogger's network age (e.g., how long ago she joined) has no effect on her retention. Our work has theoretical implications for the social behavior literature of bloggers, and practical implications for potential community blogging platform developers.
Bridging Structural Holes Scholarly Collaboration in Online Social Networks BIBAFull-Text 8
  Marco T. Bastos
In this paper we evaluate the interplay between scholarly social networks and academic output. To this end, we tested the hypotheses that the activity of users on academic social networks is associated with academic output. The quantitative data used for this study was collected from the publicly-accessible scholarly social network HASTAC and complemented with a qualitative survey collected from 123 students and recent alumni of the HASTAC Scholars Program. Our results partially support the hypothesis that activity in scholarly networks is associated with academic output, and show that Scholars who both collaborated online and published their academic work together bridge structural holes in the network. Finally, we discuss the generalizability of our findings and argue that online activity and academic output are both likely driven by networked Scholars devoted to academic research.
Assessing Sentiment Segregation in Urban Communities BIBAFull-Text 9
  Yu-Ru Lin
In this work, we attempt to examine the relationship between the social antecedents of urban neighborhoods and the citizens' everyday sentiment expression left in social media. Using Twitter users' geocoded messages posted within neighborhoods in the city of Pittsburgh, we first construct sentiment profiles for each neighborhood. We identify neighborhoods with relatively stable sentiment profiles and analyze the correlations between their sentiment orientations and the neighborhoods' demographic attributes including age, public safety, education, and ethnicity. The first order correlations show an interesting association between these neighborhood attributes and particular types of sentiments. We further group neighborhoods with similar demographic characteristics and observe that between two demographic groups, sentiments diverge in several sentiment categories including joy and disgust. This paper presents empirical evidence of sentiment segregation corresponding to the neighborhood contexts, which has implications for monitoring public attitudes and community integration.
Role of Trust in Evolution of Scientific Collaboration Networks BIBAFull-Text 10
  Avijit Gayen; Joydeep Chandra
Recent studies indicate that collaborations among researchers reflect a social relation among them. The strength of the relation is often determined by the number of publications being made by the collaborating researchers. Thus this relation among the collaborators can be represented by a weighted network, where the nodes represent the authors and the links weights are determined by the strength of the relation. In this paper, we study the evolution of such weighted networks based on the mutual trust among the authors (that we term as link trust) as well as the global trust of the authors in the network (that we term as node trust). We have identified various metrices to measure these trusts. Based on these measures we have analyzed the role of both node as well as link trust in the evolution of networks. Our observations are based on a publication data set in the area of computer science. We have also proposed suitable analytical models that closely mimics the evolution of these networks based on these trust characteristics. Our results indicate that these trust parameters play significant, yet different roles in evolution of those networks.
The Role of Peer Influence in Churn in Wireless Networks BIBAFull-Text 11
  Qiwei Han; Pedro Ferreira
Subscriber churn remains a top challenge for wireless carriers. These carriers need to understand the determinants of churn to confidently apply effective retention strategies to ensure their profitability and growth. In this paper, we look at the effect of peer influence on churn and we try to disentangle it from other effects that drive simultaneous churn across friends but that do not relate to peer influence. We analyze a random sample of roughly 10 thousand subscribers from large dataset from a major wireless carrier over a period of 10 months. We apply survival models and generalized propensity score to identify the role of peer influence. We show that the propensity to churn increases when friends do and that it increases more when many strong friends churn. Therefore, our results suggest that churn managers should consider strategies aimed at preventing group churn. We also show that survival models fail to disentangle homophily from peer influence over-estimating the effect of peer influence.
An Enhanced Collaborative Filtering with Flexible Item Popularity Control for Recommender Systems BIBAFull-Text 12
  Tu Chen; Hui Tian; Xuzhen Zhu
With the emerging and rapid development of Internet applications like social networks, E-commerce and so on, massive information has been created and stored. Recommender systems have been developed to deal with the information overload problem. Various recommendation algorithms have been proposed and Collaborative Filtering (CF) is one of the most remarkable. However, many similarity-based CFs suffer from a popularity bias problem: Popular items are frequently recommended not necessarily promoting the accuracy but making the recommendation lacking diversity. In this paper, we firstly explain how the item popularity impacts on the recommendation. Secondly, we propose an enhanced collaborative filtering approach (ECF) by adding item popularity control into a user-taste based method. Different from some other existing item popularity based CF methods, the popularity control in our approach is flexible and tunable. After that, extensive experiments are performed on two real benchmark datasets where the relationship between item popularity control and recommendation accuracy and diversity is investigated and turns out to be nonlinear. Experimental results demonstrate that temperate item popularity control can further improve the recommendation accuracy and diversity significantly, compared with the pure user-taste based method. But intemperate control makes the performance even worse Thus the flexibility is indeed essential and valuable.

Poster Abstracts

The Role of Peer Influence in Churn in Wireless Networks BIBAFull-Text 13
  Qiwei Han; Pedro Ferreira
Subscriber churn remains a top challenge for wireless carriers. In this paper, we look at the effect of peer influence on churn and we try to disentangle it from other effects that drive simultaneous churn across friends but that do not relate to peer influence. We analyze a random sample of roughly 10 thousand subscribers from large dataset from a major wireless carrier over a period of 10 months. We apply Generalized Propensity Scores to identify the role of peer influence. We show that the propensity to churn increases when friends do and that it increases more when many strong friends churn. Therefore, our results suggest that churn managers should consider strategies aimed at preventing group churn.
An Enhanced Collaborative Filtering with Flexible Item Popularity Control for Recommender Systems BIBAFull-Text 14
  Tu Chen; Hui Tian; Xuzhen Zhu
With the emerging and rapid development of Internet applications like social networks, E-commerce and so on, massive information has been created and stored. Recommender systems have been developed to deal with the information overload problem. Various recommendation algorithms have been proposed and Collaborative Filtering (CF) is one of the most remarkable. However, many similarity-based CFs suffer from a popularity bias problem: Popular items are frequently recommended not necessarily promoting the accuracy but making the recommendation lacking diversity. In this paper, we firstly explain how the item popularity impacts on the recommendation. Secondly, we propose an enhanced collaborative filtering approach (ECF) by adding item popularity control into a user-taste based method. Different from some other existing item popularity based CF methods, the popularity control in our approach is flexible and tunable. After that, extensive experiments are performed on two real benchmark datasets where the relationship between item popularity control and recommendation accuracy and diversity is investigated and turns out to be nonlinear. Experimental results demonstrate that temperate item popularity control can further improve the recommendation accuracy and diversity significantly, compared with the pure user-taste based method. But intemperate control makes the performance even worse Thus the flexibility is indeed essential and valuable.
Role of Trust in Evolution of Scientific Collaboration Networks BIBAFull-Text 15
  Avijit Gayen; Joydeep Chandra
In this paper, we study the evolution of scientific collaboration networks based on the mutual trust among the authors (link trust), as well as the global trust of the authors (node trust). We have also proposed suitable analytical models that closely mimics the evolution of these networks based on these trust characteristics. The observations, based on a publication data set in the area of computer science, indicate that these trust parameters play significant, yet different roles in evolution of those networks.
Did You Blog Yesterday? Retention in Community Blogs BIBAFull-Text 16
  Imrul Kayes; Xiang Zuo; Da Wang; Jacob Chakareski
We ask what factors cause a blogger to continue participating in the community by contributing content (e.g., posts, comments). We crawled a sample of blogger profiles (contributed 91% posts) from a popular community blogging platform "Blogster". Our results show that the male and aged (senior) bloggers, who face fewer constraints and have more opportunities in the community are more retained than others. Other bloggers pay a high degree of attention to these retained bloggers through implicit (reading posts) and explicit (writing comments) interactions. We have also found that a blogger has higher retention if her friends have also higher retention and a strong social tie reduces retention imbalance between two blogger friends. However, we found that a blogger's network age (e.g., how long ago she joined) has no effect on her retention.
Optimisation of strategy placements for public good in complex networks BIBAFull-Text 17
  Dharshana Kasthurirathna; Harrison Nguyen; Mahendra Piraveenan; Shahadat Uddin; Upul Senanayake
Game theory has long been used to model cognitive decision making in societies. While traditional game theoretic modelling has focused on well-mixed populations, recent research has suggested that the topological structure of social networks play an important part in the dynamic behaviour of social systems. Any agent or person playing a game employs a strategy (pure or mixed) to optimise pay-off. Previous studies have analysed how selfish agents can optimise their payoffs by choosing particular strategies within a social network model. In this paper we ask the question that, if agents were to work towards the common goal of increasing the public good (that is, the total network utility), what strategies they should adapt within the context of a heterogeneous network.
Enron Corporation: You're the Boss if People Get Mentioned to You BIBAFull-Text 18
  Apoorv Agarwal; Adinoyi Omuya; Jingwei Zhang; Owen Rambow
In this extended abstract we use a new type of network, which we call the mention network, for the task of dominance prediction of employees of the Enron corporation given their emails. We show that the network formed using "who mentions whom to whom" links out-performs the traditionally used Enron email network. We present a comprehensive set of experiments to conclude that organizational dominance is best predicted by capturing the number of people mentioned to a person.
How to Become a More Popular Thread on Tianya Club BIBAFull-Text 19
  Jindong Chen; Lina Cao; Xijin Tang
In Bulletin Board System, when an author submits a post to start a thread, what kinds of elements affect the popularity of this thread? To address this issue, Tianya Zatan board of Tianya Club is selected as data source for this study. Through database and online data, the daily new threads with high degree of online interactions in 2012 are collected for analysis. To explore the key elements relating to the popularity of thread, several elements are analyzed using different methods: the topics of original posts are based on Latent Dirichlet Allocation, the high frequency words of titles, the basic features (the length of titles, the titles with/without picture information, and the length of the content of original posts) and reply modes are based on statistics. Finally, several practical tips for an author to promote the popularity of the thread are given.
Knowledge Barter-Auctioning: An Incentive for Quality of User-Generated Content in Online Communities BIBAFull-Text 20
  Qijin Ji; Haifeng Shen; Yuqing Mao; Yanqin Zhu
Incentives play a pivotal role in stimulating user-generated content (UGC). Non-financial social incentives are generally effective in boosting the quantity, but have limited effect on the quality. Conversely, financial incentives generally motivate better quality, but often complicate the efforts to attract quantity. We propose knowledge barter-auctioning, a non-financial remunerative mechanism that is particularly effective in stimulating the quality of UGC yet without detriment to its quantity by allowing a vendor to choose the best barter partner in order to maximise their expected revenue.

1st International Symposium on Recent Advances in Social Computing 2014

A gender lens perspective of the use of social network in higher education in Malaysia and Australia BIBAFull-Text 21
  Kung-Keat Teoh; Tahereh Pourshafie; Vimala Balakrishnan
The use of social network sites (SNS) such as Facebook, Twitter, LinkedIn, Pinterest, Google Plus+, Tumblr, and Instagram, among others, has increased at a very fast pace in the last few years. In tandem with its rising popularity, especially among teenagers, many academics in higher education have been experimenting with its use in formal and less formal ways, in classroom teaching. Studies on the use of SNS in higher education indicate mixed results. While some academics found that SNS only distracts students from actual study and do not improve academic performance, others discovered that it improves communication and teacher-student relationships. Most however, agree that SNS's popularity with students makes it a very useful tool to exploit for classroom teaching and management. There are very few studies which look into the effect of gender on the use of SNS in education. While studies have concluded that men and women approach and use SNS in slightly different ways, there is little in existing literature which tells us about how the use of SNS in higher education differs between men and women. This paper discusses research on the use of SNS in higher education by both genders. It details the results of a survey conducted in Malaysia and Australia and highlights how men and women perceive SNS use in higher education based on a framework built on Push Pull and Mooring theory.
Predicting Controversy of Wikipedia Articles Using the Article Feedback Tool BIBAFull-Text 22
  Michal Jankowski-Lorek; Radoslaw Nielek; Adam Wierzbicki; Kazimierz Zielinski
Different points of view, opinions and controversies constitute the inherent part of modern society. Early detection of controversy is crucial for increasing productivity in peer production systems. The paper presents novelty approach to detecting controversial articles on the Wikipedia based on users ratings from Article Feedback Tool. The performance of proposed approach is on par with state-of-the-art solutions, but may also be applied outside Wikipedia-like systems. Additionally, emotion polarity measures can be used to locate controversial parts of articles, based on talk pages sections. With help of proposed algorithms, all articles in English Wikipedia have been tagged as either controversial or non-controversial. The dataset has been published and can be used by other researchers.