H6513 Information Organisation
Social Networking Sites (SNS)
Users, Content, User Activity/Behavior
Copyright By PowCoder代写 加微信 powcoder
Profile of SNS users/use
Younger users, undergraduates and women are more likely to use SNS, use them more frequently and have more SNS friends
Women were much more likely to use Twitter and Instagram than men (survey at a university in Singapore)
Undergraduate men used blogs, media-sharing sites (mainly YouTube), social Q&A sites, user review sites and wiki sites (mainly Wikipedia) more often than female students did (survey at a university in the U.S.)
Profile：Timeline，wall（个人主页） vs newsfeed，home personal
Page：Facebook metrics
Profile of SNS users/use
Women use SNS for maintaining existing relationships, whereas men use it more for developing new contacts
Men use SNS more for task-oriented reasons and less for interpersonal purposes
Men are also more likely than women to post risky information online
International students use SNS to keep in touch with family and friends in their home countries, and obtain social support
Profile of SNS users/use
More undergraduates use Twitter, YouTube and Instagram than graduate students (survey at a university in Singapore)
More graduate students use LinkedIn
Chinese international students use mainly Chinese SNS such as Renren, Qzone (QQ), and WeChat
Multi-country comparisons
Oh and Kim (2014) compared students at a U.S. university with a Korean university — in their use of social media sites for health information
Fitness and diet and nutrition were the most searched topics for both groups
American students used social networking sites more than Korean students
and more likely to search for “medicine” and for information on sexually transmitted diseases.
April 2014 survey
Nanyang Technological University, Singapore
408 respondents
Singapore citizens (37%)
Chinese nationals (45%)
Undergrad vs graduate students
More undergraduates use
Twitter — 42% undergrads vs. 20% graduate students
YouTube — 75% undergrads and 60% grad students
Instagram — 55% undergrads and 26% grad students
More graduate students use LinkedIn
39% grad students versus 20% undergrads
Singaporeans vs. Chinese nationals
Chinese SNS such as Renren, Qzone (QQ), and WeChat — mostly used by Chinese students
More Singaporean undergrads use
Facebook — 95% Singaporeans vs. 79% Chinese
Twitter — 50% Singaporeans and 26% Chinese
Instagram — 67% Singaporeans and 34% Chinese
Gender differences
Singaporean students: a higher proportion of women use most of the SNS than men
Big differences found for Twitter (46% women versus 29% men), and Instagram (65% women and 38% men).
For Chinese students, gender differences are not so clear
more women are using Google+ (29% women and 19% men) and Instagram (33% women and 21% men)
Primary social networking platforms
Singaporean students:
men use Facebook as the primary SNS (85%)
women use a variety of primary SNS (18% Instagram and 10% Twitter).
Chinese students:
women selected WeChat (42% women and 36% men)
men selected Renren (19% men and 8% women).
Types of information shared
Top 3 types of information
funny clips and jokes
international news
national or local news
Followed by six types of information
social events, food and beverage products, travel destinations/itineraries, health tips, music recommendations and hobby related information.
Content analysis of Facebook posts
Content analysis of a thousand Facebook posts from 20 participants — mainly aged 30 to 50 years
Few information requests and few instances of information provision (in response to information requests).
Information requests tend to be generic in nature, and not sensitive, embarrassing or personal.
E.g. “Groupon promotion. Anyone wanna go? Need 2 pax next weekend!”
Content analysis of Facebook posts
Posts are mostly in the form of content sharing of existing external content (websites, photos and YouTube videos), rather than user-generated content.
Photos are used extensively in personal updates (nearly half the time.)
a shift from recording and sharing information in textual form, epitomized by blogs.
Some opinion and recommendation posts, but mainly endorsements of recommendations found on websites, rather than reviews by the Facebook user.
Topics of sharing on Facebook
(Aside from personal updates)
Entertainment (especially humorous and music content, often from YouTube)
Food (mainly in the form of photos and links to food-related websites)
Life lessons and quotes
Health (mainly wellness/lifestyle tips and advice on common health issues)
Pets and hobby
Users’ perception of social networking
SNS not perceived by users as a source of information, but as a means for networking, maintaining relationships, and keep abreast of happenings in their friends’ lives
Perhaps more information encountering, than information searching takes place
Metrics of social media presence
Benchmark: overall sense of social media presence, e.g. such as likes, followers, and mentions.
Audience: e.g., impressions, reach, demographics, or the location of your audience and when they’re tuning in.
Engagements: how your audience is connecting with you through engagements like classic likes, comments, and shares.
Conversions: the ‘so-what’ factor. What’s the business impact of what you’re posting on social media? Any metric that tracks clicks or leads.
Opportunities: opportunities drawn from the metrics. E.g., user-generated links, hashtags, and general brand monitoring.
Kim, Jonah . (2017, July 17). Getting social with data analytics. CMO Innovation.
Getting social with data analytics
Kim, Jonah . CMO Innovation ; Newton (Jul 17, 2017).
Case studies
Analysis of Facebook sites of 3 drug store chains in the US
Quantitative measures
Level of engagement (manually collected): no. of fans/followers, no. postings, comments, likes, frequency of posting, response time
Spikes caused by holidays, promotions, special events
No. of likes is correlated with no. of comments/visits
No. of comments correlated with no. of visits
Drug stores who joined Facebook earlier has more likes and comments
He, W., Chen, Y., Tian, X., & Chong, D. (2016). Actional social media competitive analytics for understanding customer experiences. Journal of Computer Information Systems, 56(2), 145-155
He, W., Chen, Y., Tian, X., & Chong, D. (2016). Actional social medi competitive analytics for understanding customer experiences.
Journal of Computer Information Systems, 56(2), 145-155
Text mining results: concept maps of user postings
He, W., Chen, Y., Tian, X., & Chong, D. (2016). Actional social medi competitive analytics for understanding customer experiences. Journal of Computer Information Systems, 56(2), 145-
He, W., Chen, Y., Tian, X., & Chong, D. (2016). Actional social medi competitive analytics for understanding customer experiences. Journal of Computer Information Systems, 56(2), 145-
He, W., Chen, Y., Tian, X., & Chong, D. (2016). Actional social medi competitive analytics for understanding customer experiences. Journal of Computer Information Systems, 56(2), 145-
Social media competitive analysis and text mining: A case study in the pizza industry
He, Wu; Zha, Shenghua; Li, Ling . International Journal of Information Management ; Vol. 33, Iss. 3, (Jun 2013): 464.
Companies are using social media tools such as Facebook and Twitter to provide various services and interact with customers. As a result, a large amount of user-generated content is freely available on social media sites.
To increase competitive advantage and effectively assess the competitive environment of businesses, companies need to monitor and analyze not only the customer-generated content on their own social media sites, but also the textual information on their competitors’ social media sites.
This paper describes an in-depth case study which applies text mining to analyze unstructured text content on Facebook and Twitter sites of the three largest pizza chains: Pizza Hut, Domino’s Pizza and ‘s Pizza. The results reveal the value of social media competitive analysis and the power of text mining as an effective technique to extract business value from the vast amount of available social media data.
Organization Mining Using Online Social Networks
Map an organization’s informal social network topology based solely on publicly available data. Can be utilized to study the diffusion of information inside the organization; to identify organizational structural problems, such as structural holes.
Use the organization’s structure to discover hidden leadership roles within the organization, pinpoint employees with leadership roles and analyze these employees’ inner organizational links to assist in constructing better working groups
Use the organization’s structure to identify communities inside the organization. This could identify which communities are dominant or weak, and which ones are functioning well or poorly.
Perform qualitative analysis of these leadership roles and communities
Fire, M., & Puzis, R. (2016). Organization Mining Using Online Social Networks.
Netw Spat Econ (2016) 16:545–578. DOI 10.1007/s11067-015-9288-4
Fire, M., & Puzis, R. (2016). Organization Mining Using Online Social Networks
Netw Spat Econ (2016) 16:545–578
DOI 10.1007/s11067-015-9288-4
Discovering Social Bursts by Using Link Analytics on Large-Scale Social Networks
Jung, . Mobile Networks and Applications, 22(4) (Aug 2017): 625-633.
Detecting and understanding social events from SNS has been investigated in many different contexts. Most of the studies have focused on detecting bursts based on textual context.
We propose a novel framework on collecting and analyzing social media data for i) discovering social bursts and ii) ranking these social bursts.
Firstly, we detect social bursts from the photos textual annotations as well as visual features (e.g., timestamp and location); and then effectively identify social bursts by considering the spreading effect of social bursts in the spatio-temporal contexts.
Secondly, we use these relationships among social bursts (e.g., spatial contexts, temporal contexts and content) for enhancing the precision of the algorithm. Finally, we rank social bursts by analyzing relationships between them (e.g., locations, timestamps, tags) at different period of time.
Community detection in social networks using user frequent pattern mining
Moosavi, S.A.; Jalali, M.; Misaghian, N.; Shamshirband, S.; Anisi, M.H.
Knowledge and Information Systems ; Vol. 51, Iss. 1, (Apr 2017): 159-186.
The detection of communities in social network data, including ‘similar’ nodes is a challenging topic. Online social networks, in addition to having graph structures, include effective user information within networks. Using this information leads to enhance quality of community discovery.
In this study, a method of community discovery is provided. Besides communication among nodes to improve the quality of the discovered communities, content information is used as well.
This is a new approach based on frequent patterns and the actions of users on networks, particularly social networking sites where users carry out their preferred activities. First, based on the interests and activities of users on networks, some small communities of similar users are discovered, and then by using social relations, the discovered communities are extended. The F-measure is used to evaluate the results of two real-world datasets (Blogcatalog and Flickr).
Parallel Graph , Andrew; Nguyen, Donald; Pingali, Keshav.
Communications of the ACM ; Vol. 59, Iss. 5, (May 2016): 78.
The study of graphs began in the 18th century with Euler’s work on the “Bridges of Konigsberg” problem, but it is only since the creation of the Web two decades ago that large-scale parallel computers have been used to study graph properties.
Today, this field, known as “parallel graph analytics,” touches all your lives, even if you are not aware of it. When you use a Web search engine or get a friend recommendation on Facebook, graph analytics is at work behind the scenes.
There are three main challenges in performing computations on these graphs — large graph sizes, diversity in graph structure, and the complex patterns of parallelism in graph analytics applications.
Most current parallel abstractions and implementations fail to provide solutions for at least one of them. Ongoing research in parallel graph analytics spans the gamut, from new domain-specific languages to novel processor architectures for supporting graph analytics and is summarized in the online appendix.
程序代写 CS代考 加微信: powcoder QQ: 1823890830 Email: powcoder@163.com