The workshop will introduce easy-to-use software developed by the Laboratory for Internet Studies to mine and analyze social media.
First, we will get acquainted with two packages that permit you download full-text and relational data from the Russian LiveJournal and the leading Russian SNS VKontakte: BlogMiner and VKMiner. BlogMiner permits massive automatic download and stores data in a relational SQL database, while VKMiner produces and easier output as a set of Excel tables and performs downloading operations one by one at user’s command. BlogMiner demands installation of extensive software and will be demonstrated only, while VKMiner is easy to install at personal notebooks and it will be practiced on. Besides downloading, VKMiner also performs network construction.
Second, we will introduce TopicMiner – a user-interface equipped software for automatic detection of topical structure in large collections of texts. Data may be imported from blogs, social networks or other sources in the form of txt. files, and more than a million of texts may be processed. The algorithm of analysis is language-independent, although would the user wish proper text preprocessing, he/she would need to attach a stemming package for his/her language of interest. We will practice with this tool as well.
No knowledge of math or coding skills are needed for this workshop.
Workshop 2: Robert Ackland "Hyperlink network analysis with VOSON"
This workshop provides an introduction to hyperlink network analysis in the context of social science research. The workshop begins with a brief overview of hyperlink network research, including a comparison of the disciplinary perspectives on hyperlink networks: information science (hyperlink networks as citation networks), media studies (hyperlink networks as issue networks) and social science (hyperlink networks as social networks). The remainder of the workshop involves practical training in the VOSON software for constructing and analysing hyperlink networks including: choosing appropriate seed sites, web crawler parameters, data preparation (how to control the merging of sub-sites and sub-domains into single network nodes), network analysis and text analysis. The workshop finishes with a demonstration of how VOSON hyperlink network data can be exported for use with third-party tools such as Gephi (for network visualisation) and R/statnet (for exponential random graph models).
Although this is not a highly technical workshop, it is assumed that workshop participants already have familiarity with basic social network concepts. To use the VOSON software, participants will need to register for a free VOSON user account at least 24 hours before the workshop. For registration and more information on the VOSON software see http://www.uberlink.com. Running VOSON requires a web browser (Firefox/Chrome/Safari - it does not work with IE) and an Internet connection.
|Robert Ackland is an Associate Professor in the Australian Demographic and Social Research Institute at the Australian National University and leads the Virtual Observatory for the Study of Online Networks project. His PhD was in economics, focusing on index number theory in the context of cross-country comparisons of income and inequality. Robert has been studying online social and organisational networks since 2002 and his research has been funded by five Australian Research Council grants. His research has appeared in journals such as the Review of Economics and Statistics, Social Networks, Computational Economics, Social Science Computer Review,and the Journal of Social Structure. The VOSON project, which was established in 2005, aims to advance the social science of the Internet by conducting research, developing research tools, and providing teaching and research training. The VOSON software for hyperlink network construction and analysis has been publicly available since 2006 and has been used by over 1500 researchers worldwide. Robert established the Social Science of the Internet specialisation in the ANU's Master of Social Research in 2008, and his book Web Social Science: Concepts, Data and Tools for Social Scientists in the Digital Age (SAGE) was published in July 2013.|
More information can be found here: https://researchers.anu.edu.au/researchers/ackland-rj