Socio semantic networks of research publications in learning analytics community
page 1Socio-semantic Networks of ResearchPublications in the Learning AnalyticsCommunitySoude Fazeli, PhD candidateDr. Hendrik DrachslerProf. Dr. Peter Sloep
page 2Agenda1. Introduction2. Motivation3. Data processing4. Network visualization5. Discussion and conclusion
page 31. Introduction• Presenting visualization of the authors and papers network• Carrying out a deeper analysis of the generated networks• The main aim• To use such a graph of authors and papers to recommend similaritems to a target user2442105111927020406080100120140LAK 2011 LAK 2012 JETS2012PapersAuthors
page 42. Motivation• A list of recommended authors and papers• To plan the conference participation more efficiently andeffectively• Awareness support for researchers (Reinhardt et al., 2012; Fisichella et al.,2010; Ochoa et al., 2009; Henry et al., 2009)• Scientific recommender systems (Huang et al., 2002; Wang & Blei, 2010)• Such a priority list• Support the awareness of the attendees• Empower the network of like-minded authors in the attendees’particular research focus
page 5• RQ1. How are the authors connected and whichauthors share more connections and are morecentral in terms of sharing commonalities with theothers?• RQ2. How are the papers connected to eachother in terms of similarity?
page 61. Finding patterns of similarity between authors and papers2. Visualizing networks of the LAK authors and papers
page 73. Data processing3.1. Tag clouds• The TF-IDF algorithm• Weighted list of the most commonly used terms in researcharticles• Using default algorithm provided by Mahout on the text filesextracted from the RDF files• Removing the stop words• Setting the configuration variables within Mahout to 90%• Outcome• A so-called dictionary of all the terms in the LAK dataset• A binary sequence file including the TF-IDF weighted vectors
page 83. Data processing3.2. Computing similarity• Using T-index algorithm (Fazeli et al., 2010)• Collaborative filtering recommender algorithm• Generates a graph of users• The nodes are users and the edges show the relationship betweenusers• Originally makes recommendations based on the ratings data of users• Extending the T-index algorithm• Process tags and keywords extracted from the linked data• Using Jena APIs to• Process RDF files• Handle Ontology Web Language (OWL) files describing the generatedgraph of authors and papers
page 94. Network visualization4.1. Author network (made by Welkin)
page 104. Network visualization4.1. Author networkThe degree centrality of the top ten central authors121928571645550 4945 449657 5546 4536 352217 16020406080100120140u1 u2 u3 u4 u5 u6 u7 u8 u9 u10Then first ten central authorsindegreen=10n=5
page 114. Network visualization4.2. Paper network
page 124. Network visualization4.2. Paper network343024 2321 20 19 18 17 16585147 464234 33 3127 26010203040506070p1 p2 p3 p4 p5 p6 p7 p8 p9 p10n=5n=10The degree centrality of Top ten papers
page 13• RQ1. How are the authors connected and whichauthors share more connections and are morecentral in terms of sharing commonalities with theothers?• RQ2. How are the papers connected to eachother in terms of similarity?
page 145. Discussion and conclusion5.1. RQ1The first ten central authorsAuthor DegreeHendrik Drachsler 116Kon Shing Kenneth Chung 87Wolfgang Greller 80Javier Melenchon 66Brandon White 59Vania Dimitrova 50Erik Duval 45Rebecca Ferguson 44Anna Lea Dyckhoff 40Simon Buckingham Shum 39
page 15• RQ1. How are the authors connected and whichauthors share more connections and are morecentral in terms of sharing commonalities with theothers?• RQ2. How are the papers connected to eachother in terms of similarity?
page 165. Discussion and conclusion5.2. RQ2Paper AuthorsLearning Dispositions and TransferableCompetencies: Pedagogy, Modelling andLearning AnalyticsSimon Buckingham-Shum,Ruth Deakin CrickThe Pulse of Learning AnalyticsUnderstandings and Expectations from theStakeholdersHendrik Drachsler,Wolfgang GrellerSocial Learning Analytics: Five Approaches Rebecca Ferguson,Simon Buckingham-ShumMulti-mediated Community Structure in aSocio-Technical NetworkDan Suthers, Kar Hai ChuModelling Learning & Performance: A SocialNetworks PerspectiveWalter Christian Paredes,Kon Shing Kenneth ChungTeaching Analytics: A Clustering andTriangulation Study of Digital Library UserDataBeijie Xu,Mimi M ReckerMonitoring Student Progress Through TheirWritten "Point of Originality"Johann Ari Larusson,Brandon WhiteLearning Designs and Learning Analytics Lori Lockyer,Shane DawsonA Multidimensional Analysis Tool forVisualizing Online InteractionsEunchul Lee,Mhammed AbdousUsing computational methods to discoverstudent science conceptions in interview dataBruce SherinThe top ten central papers
page 175. Discussion and conclusion• The central authors and top ten papers will appearmore often in the top recommendation list• Although most of the central authors also appear intop ten papers’ list, the order is not the same• Some authors has more than one paper• Not each and every one of the authors’ papersindividually has the highest similarity to the otherpapers
page 18Soude FazeliPhD candidateOpen University of the NetherlandsCentre for Learning Sciences and Technologies(CELSTEC) PO-Box 29606401 DL Heerlen, The Netherlandsemail: firstname.lastname@example.org