Gruzd, Anatoliy
Permanent URI for this collectionhttps://hdl.handle.net/10222/15308
Browse
Recent Submissions
Item Open Access Investigating biomedical research literature in the blogosphere: a case study of diabetes and glycated hemoglobin (HbA1c)(2012-01) Gruzd, Anatoliy; Black, Fiona A.; Le, Thi Ngoc Yen; Amos, KathleenObjective: The research investigated the relationship between biomedical literature and blogosphere discussions about diabetes in order to explore the role of Web 2.0 technologies in disseminating health information. Are blogs that cite biomedical literature perceived as more trustworthy in the blogosphere, as measured by their popularity and interconnections with other blogs? Methods: Web mining, social network analysis, and content analysis were used to analyze a large sample of blogs to determine how often biomedical literature is referenced in blogs on diabetes and how these blogs interconnect with others in the health blogosphere. Results: Approximately 10% of the 3,005 blogs analyzed cite at least 1 article from the dataset of 2,246 articles. The most influential blogs, as measured by in-links, are written by diabetes patients and tend not to cite biomedical literature. In general, blogs that do not cite biomedical literature tend not to link to blogs that do. Conclusions: There is a large communication gap between health professional and personal diabetes blogs. Personal blogs do not tend to link to blogs by health professionals. Diabetes patients may be turning to the blogosphere for reasons other than authoritative information. They may be seeking emotional support and exchange of personal stories.Item Open Access Trends in Scholarly Use of Online Social Media(Position paper presented at the Workshop on Changing Dynamics of Scientific Collaboration, the 44th Annual Hawaii International Conference on System Sciences (HICSS), January 4-7, 2011, Kauai, HI, USA., 2011-01-04) Gruzd, Anatoliy; Staves, KathleenItem Open Access Blogging with CONTEXT: A context-aware information retrieval system for bloggers(ACM, 2010) Gruzd, Anatoliy; Wong, J.The poster describes the development process and evaluation of a context-aware information retrieval system for blog authors, called CONTEXT. As a blogger writes a post, the system automatically retrieves and displays links to web resources (web sites, news stories, video, etc) that are relevant to the bogger’s entry. CONTEXT continuously monitors the blog post for new search keywords to find and display the most relevant resources to the blogger. The main goal of this system is to inform the blogger in real time of other related discussions that are going on in the blogosphere or elsewhere and give her/him a chance to be part of the ‘global’ conversation and thus improve his/her entry by incorporating some of the suggested resources into a post. Our expectation is that CONTEXT will lead to more interactive and content-rich blog entries, in which bloggers are not just expressing their own opinions, but they are also addressing each other and building on each other’s arguments.Item Open Access The Analysis of Online Communities using Interactive Content-based Social Networks(2008) Gruzd, Anatoliy; Haythornthwaite, CarolineToday the Internet has become a convenient and ubiquitous platform for anyone with access to publish their thoughts and ideas, express their opinions, argue with their peers on various issues and, most importantly, organize and form online communities. The majority of user-generated discussions on the Internet are still text-based. Many of these discussions are archived and readily available to organizers, developers and researchers of online communities. Being able to evaluate the internal processes of such communities is; however, as yet, there is still no easy or cost effective method to study and analyze this ever growing mountain of textual data in real-time. This paper describes a new, automated procedure and a prototype of our web application for making sense of online activities in real time.Item Open Access Write While You Search: Ambient Searching of a Digital Library in the Context of Writing(2006) Gruzd, Anatoliy; Twidale, MichaelWe consider ideas for a tighter integration of searching a digital library while writing a paper. A prototype system based on web services is described which allows us to explore the design space of ambient search tools to support and inspire the writing process.Item Open Access Name Networks: A Content-Based Method for Automated Discovery of Social Networks to Study Collaborative Learning(2009) Gruzd, AnatoliyAs a way to gain greater insight into the operation of Library and Information Science (LIS) e-learning communities, the presented work applies automated text mining techniques to text- based communication to identify, describe and evaluate underlying social networks within such communities. The main thrust of the study is to find a way to use computers to automatically discover social ties that form between students just from their threaded discussions. Currently, one of the most common but time consuming methods for discovering social ties between people is to ask questions about their perceived social ties via a survey. However, such a survey is difficult to collect due to the high cost associated with data collection and the sensitive nature of the types of questions that must be asked. To overcome these limitations, the paper presents a new, content-based method for automated discovery of social networks from threaded discussions dubbed name networks. When fully developed, name networks can be used as a real time diagnostic tool for educators to evaluate and improve teaching models and to identify students who might need additional help or students who may provide such help to others.Item Open Access Automated Discovery of Emerging Online Communities Among Blog Readers: A Case Study of a Canadian Real Estate Blog(2009) Gruzd, AnatoliyMore than 184 million people worldwide have started a web blog, that collectively attracted at least 346 million blog readers. Due to their popularities, web blogs have been the focus of many recent Internet studies. Aside from being a great publishing platform, many of these studies confirmed the fact that modern blogs with commenting-capabilities are also great places for meeting like-minded individuals and forming new social relationships. As a result, it is not surprising that there is also a growing interest in discovering and characterizing online communities that tend to naturally form around some web blogs. Traditional analyses of blog are hampered by the expensive and time consuming processes. To address these problems, this paper proposes an automated approach for the discovery of social networks among blog readers just from their comments posted to a blog. This new approach is called “name network” and is an integral part a companion web-based tool called Internet Community Text Analyzer or ICTA for short (http://textanalytics.net). The “name network” method is capable of automatically discovering a social network among blog readers that accurately represents group dynamics.Item Open Access Web APIs: A Step towards Greater Mobility of User-Created Data across Social Networking Websites and Their Implications for Research in Information Behavior(2007) Gruzd, AnatoliyAs Internet users are joining more online communities such as Facebook and MySpace, they are also becoming more prolific content creators. But unfortunately, the task of managing and exchanging content between their various online social networking (SN) communities remains cumbersome and time consuming. This is primarily because most of websites “lock” users’ data on their servers and do not provide an effective/efficient data sharing and exchange protocols. A better way for users to integrate and exchange data across online SN communities is to use web APIs (Application Programming Interface) – a mechanism that allows a site to provide “back door” access to its content and services via a standardized machine-readable protocol. Any website can deploy web APIs to allow its users to integrate data from external sites. As these new technologies and techniques become more widely available, it will make user-created data even more mobile. This will likely lead to some changes in users’ information behaviours.Item Open Access Automated Discovery and Analysis of Social Networks from Threaded Discussions(2008) Gruzd, Anatoliy; Haythornthwaite, CarolineTo gain greater insight into the operation of online social networks, we applied Natural Language Processing (NLP) techniques to text-based communication to identify and describe underlying social structures in online communities. This paper presents our approach and preliminary evaluation for content-based, automated discovery of social networks. Our research question is: What syntactic and semantic features of postings in a threaded discussions help uncover explicit and implicit ties between network members, and which provide a reliable estimate of the strengths of interpersonal ties among the network members? To evaluate our automated procedures, we compare the results from the NLP processes with social networks built from basic who-to-whom data, and a sample of hand-coded data derived from a close reading of the text. For our test case, and as part of ongoing research on networked learning, we used the archive of threaded discussions collected over eight iterations of an online graduate class. We first associate personal names and nicknames mentioned in the postings with class participants. Next we analyze the context in which each name occurs in the postings to determine whether or not there is an interpersonal tie between a sender of the posting and a person mentioned in it. Because information exchange is a key factor in the operation and success of a learning community, we estimate and assign weights to the ties by measuring the amount of information exchanged between each pair of the nodes; information in this case is operationalized as counts of important concept terms in the postings as derived through the NLP analysis. Finally, we compare the resulting network(s) against those derived from other means, including basic who-to-whom data derived from posting sequences (e.g., whose postings follow whose). In this comparison we evaluate what is gained in understanding network processes by our more elaborate analysis.Item Open Access Analyzing Networked Learning Texts(2008) Haythornthwaite, Caroline; Gruzd, AnatoliySocial interactions are essential in understanding the collaborative processes in networked learning environments. Although individuals may learn by retrieving information from online archives, dictionaries and encyclopaedia, it is the interaction with others with similar, perhaps narrowly enjoyed interests that fuels the benefits of networked learning. This paper presents our ongoing work on a novel, automated method for extracting interaction data from threaded discussions of networked learning groups. Using natural language processing, the proposed method reduces large text-based datasets to community and conversational essentials that show the relations of importance to group members. By studying these relations, we hope to identify what matters in terms of learning in the online interaction space and to provide useful representations of online conversations to help networked learners (instructors and students) better understand the social environment in which they are participants. To do so also requires making accurate determinations of who is talking to whom. This paper discusses the methodological issues associated with extracting names from networked learning texts and our procedures for enhancing network information through new techniques of name extraction.Item Open Access N is for Network: New Tools for Mapping Organizational Change(2010) Steffen-Fluhr, N.; Gruzd, Anatoliy; Collins, R.; Osatuyi, B.Understanding network dynamics is important for underrepresented minorities and women in technological organizations, who can easily spend their entire careers on the periphery, far away from the flow of information at the core. We explore this problem by describing the results of a new study of faculty research networks conducted by the NSF-funded ADVANCE program at the New Jersey Institute of Technology (NJIT). Using tools such as ORA to analyze a database that contains nearly a decade of information about NJIT faculty publications, ADVANCE researchers have created dynamic co-authorship maps that provide an aerial view of the organizational landscape as it changes over time. By giving faculty and administrators guided access to such maps, university change agents can promote mentoring policies and practices that support the advancement of women and minority faculty.