Iknow ranking sem_info_v9.0__2012.09.07_anjorin
Upcoming SlideShare
Loading in...5
×
 

Iknow ranking sem_info_v9.0__2012.09.07_anjorin

on

  • 256 views

Presentation at the Iknow 2012 conference in Graz, Austria.

Presentation at the Iknow 2012 conference in Graz, Austria.

Statistics

Views

Total Views
256
Views on SlideShare
256
Embed Views
0

Actions

Likes
0
Downloads
1
Comments
0

0 Embeds 0

No embeds

Accessibility

Categories

Upload Details

Uploaded via as Adobe PDF

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment

Iknow ranking sem_info_v9.0__2012.09.07_anjorin Iknow ranking sem_info_v9.0__2012.09.07_anjorin Presentation Transcript

  • Ranking Resources in Folksonomies By Exploiting Semantic Information i-KNOW 2012, Saarbrücken Users Tags Resources Research Talk n Perso Typ e Loca tion Ranking Topic Algorithms Event Oth Act er ivit yThomas Rodenhausen SlideshareMojisola AnjorinRenato Domínguez GarcíaChristoph Rensing Prof. Dr.-Ing. Ralf SteinmetzRalf Steinmetz KOM - Multimedia Communications LabIknow_Ranking_Sem_Info_v9.0__2012.09.07_MA.pptx 7-Sep-12© author(s) of these slides including research results from the KOM research network and TU Darmstadt; otherwise it is specified at the respective slide
  • Social Tagging ApplicationsSocial tagging applications are used to organize, classify, manage and share knowledge resources !  Tags are freely chosen keywords attached to resources !  Tags often describe an aspect of the resource Lora o Aroy Graz Key note Dial E I-know for 2012 Events Sema n Pre pa rin W tic eb g Con for fer enc e KOM – Multimedia Communications Lab 2 www.wordle.net
  • Recommendations in Social TaggingApplications KOM – Multimedia Communications Lab 3
  • Overview !  Motivation !  Basics !  Folksonomy !  Folksonomy Extended by Tag Types !  Graph-based Resource Recommendation !  Challenge: Concept Drift !  AspectScore & InteliScore !  Evaluation Methodology and Metrics !  Results !  Conclusion & Future Work KOM – Multimedia Communications Lab 4
  • Folksonomy Users Tags ResourcesA folksonomy is a quadrupleF:= (U, T, R, Y), where Research TalkU – UsersT – TagsR – ResourcesY ⊆ U ! T ! R - tag assignment Ranking Algorithms Slideshare [Hotho et al. 2006] KOM – Multimedia Communications Lab 5
  • Folksonomy Extended by Tag Types Users Tags ResourcesAn extended folksonomyFA:= (U, T, R, A, Y) where Research TalkU – Users Perso n TypT – Tags e Loca tion TopicR – Resources Event Oth Act erA – Tag Types ivity Ranking AlgorithmsY⊆U!T!RxAA = {Topic, Resource Type, Location,Person, Event, Activity, Other} Slideshare[Böhnstedt et al. 2009] KOM – Multimedia Communications Lab 6
  • Graph-based Resource Recommendation Recommendation List Item Score 3 P2P1 1 1 Graph-based r1 0.9 2 Ranking r2 0.7 4 1 Algorithm 2 1 r3 0.5 P3 2 P4 r4 0.2 Folksonomy Graph Scorer e.g. PageRank, HITS Ranked Resources KOM – Multimedia Communications Lab 7
  • Adapted PageRank [Hotho et al. 2006] " " Dancing$%&()*+,& Tango ! l 0 Festiva 0 # # "-. " #-. 1 ! PageRank‘s intelligent surfer model #-. Buenos " The ranking of a node is determined by how "-. Aires often the surfer visits the node 0 Buenos Adjoining edges are followed with a certain Aires probability – determined by the edge weights 0 " The query node acts as the starting point and focus i.e. the surfer returns to this node with ! a certain probability – determined by the node weights KOM – Multimedia Communications Lab 8
  • Challenge: Concept DriftConcept drift is a challenge for graph-based ranking algorithms !  e.g. Ambiguous tags can cause concept drift as a single tag might represent multiple semantic concepts ? football News about Messi ? FC Barcelona Website Dallas Cowboys‘ Website KOM – Multimedia Communications Lab 9
  • Overview !  Motivation !  Basics !  Folksonomy !  Folksonomy Extended by Tag Types !  Graph-based Resource Recommendation !  Challenge: Concept Drift !  AspectScore & InteliScore !  Evaluation Methodology and Metrics !  Results !  Conclusion & Future Work KOM – Multimedia Communications Lab 10
  • InteliScore The semantic information gained from the semantic relatedness between tags is used to reduce concept drift Dancing Tango Festival Semantic Relatedness (XESA) 0.005 Buenos Aires XESA calculates the semantic relatedness between pairs of tokens (tags) using the English Wikipedia as reference corpus [Scholl et al. 2010]Source: wikipedia.org KOM – Multimedia Communications Lab 11
  • AspectScoreTag types help to alleviate concept drift !  Tags are disambiguated with respect to different aspects of a resource that a user may describe while tagging topic location Buenos Aires Tourism in Argentina News about Tango KOM – Multimedia Communications Lab 12
  • AspectScoreTag types help to alleviate concept drift !  e.g. by focusing on the tags describing the content of resources topic location Buenos Aires Tourism in Argentina News about Tango topic Assumption: The tags of type „Topic“ describe the content of the resources well, Google Map of Buenos Aires therefore „Topic“ Tags are given priority. KOM – Multimedia Communications Lab 13
  • AspectScore: Step 1 Buenos 1. Transform Query Node Tango Buenos Aires into Query Tags 3 Aires 1 1 User query node is transformed into tag nodes, weighted by the usage frequency of the user Assumption: Tags of a user describe the user‘s interests well [Abel 2011] KOM – Multimedia Communications Lab 14
  • AspectScore: Step 1 Query Tag 1. Transform Query Node in Query Tags Dancing Tango Festiva l Query Node Buenos Aires Buenos Aires Query Tags KOM – Multimedia Communications Lab 15
  • AspectScore: Step 2 1. Transform Query Node into Query Tags 2. Create FolksonomyGraph for each Query Tag KOM – Multimedia Communications Lab 16
  • AspectScore: Step 2 1. Transform Query Node " " Dancing $%&()*+, Tango ! l into Query Tags 3 Festiva 0 # # " 2. Create Folksonomy "Graph for each Query Tag ! # ! Buenos " " Aires " 0 " Buenos Aires 0 Depending on Ranking Algorithm e.g. FolkRank " ! KOM – Multimedia Communications Lab 17
  • AspectScore: Step 3 1. Transform Query Node "#"$ "#"$ Dancing ()*+",-. Tango ! l into Query Tags 3 Festiva 0 "%"$ "%"$ "#"$ 2. Create Folksonomy "#"$Graph for each Query Tag "%"$ ! ! Buenos "#"$ "#"$ 3. Adapt Edge Weights Aires "#"$ 0 Buenos "#"$& Aires 0 Edge Weights are adapted "#"$ (in several iteration steps) depending on Query Tag ! KOM – Multimedia Communications Lab 18
  • AspectScore: Step 4 1. Transform Query Node "#"$ "#"$ Dancing ()*+",-. Tango ! l into Query Tags 3 Festiva 0 "%"$ "%"$ "#"$ 2. Create Folksonomy "#"$Graph for each Query Tag "%"$ ! ! Buenos "#"$ "#"$ 3. Adapt Edge Weights Aires "#"$ 0 Buenos "#"$& Aires 4. Run Ranking Algorithm 0 Run e.g. FolkRank on the "#"$ adapted folksonomy graph ! KOM – Multimedia Communications Lab 19
  • AspectScore: Step 5 1. Transform Query Node into Query Tags 2. Create FolksonomyGraph for each Query Tag 3. Adapt Edge Weights The resulting rankings are accumulated giving preference to certain tag types 4. Run Ranking Algorithm e.g. topic tags Buenos Tango Buenos Aires 5. Accumulate Results Aires 1δ Topic 3δ Topic for each Query Node 1δ Location KOM – Multimedia Communications Lab 20
  • Overview !  Motivation !  Basics !  Folksonomy !  Folksonomy Extended by Tag Types !  Graph-based Resource Recommendation !  Challenge Concept Drift !  AspectScore & InteliScore !  Evaluation Methodology and Metrics !  Results !  Conclusion & Future Work KOM – Multimedia Communications Lab 21
  • Evaluation Methodology: LeavePostOutA post is a Pu,r= {(u,r,t)|(u,r,t) ! Y} Dancing Dancing Tango Tango Festival Festival Buenos Buenos Aires AiresFor LeavePostOut, the recommendation taskwith user as input is harder as with tag as input [Jäschke et al. 2007] KOM – Multimedia Communications Lab 22
  • Evaluation Methodology: LeaveRTOutRTr,t= {(u,r,t)|(u,r,t) ! Y} Dancing Dancing Tango Tango Festival Festival Buenos Buenos Aires AiresFor LeaveRTOut, the recommendation taskwith tag as input is harder as with user as input KOM – Multimedia Communications Lab 23
  • Evaluation CorpusBibsonomy corpus with a p-core extraction at level 5 to reduce noise and to focus on the dense portion of the corpus Before After Tag Type Count Users 7243 69 Topic 2225 Bookmark resources 281550 9 Other 486 Bibtex resources 469654 134 Resource Type 198 Tags 216094 179 Event 182 Tag assignments 2740834 3269 Person/Organisation 143 Bookmark posts 330192 51 Activity 35 Bibtex posts 526691 959 FReSET – Domínguez García et al 2012 http://www.kom.tu-darmstadt.de/research-results/downloads/software/freset/ KOM – Multimedia Communications Lab 24 Knowledge and Data Engineering Group, University of Kassel: Benchmark Folksonomy Data from Bibsonomy, version of July 7th 2011
  • Evaluation Metrics Mean Average Precision: The mean of the Average |Q| mj Precision over several queries Q 1 ￿ 1 ￿MAP(Q) = Precision(Rjk ) |Q| j=1 mj k=1 [Manning et al 2008]Mean Normalized Precision: The mean of the normalized Precision at k |Q| 1 ￿ Precisionj (k) over several queries QMNP(Q, k) = |Q| j=1 Precisionmax,j (k) KOM – Multimedia Communications Lab 25
  • Visualization of Results with Violin PlotsA violin plot is a combination of a box plot and a density trace 3rd QuartileMedian 1st Quartile [Hintze et al. 1998] KOM – Multimedia Communications Lab 26
  • Evaluation Results LeavePostOutEvaluation results for the recommendation task having tag as input KOM – Multimedia Communications Lab 27
  • Evaluation Results for LeavePostOutEvaluation results for the recommendation task having tag as input Approaches MAP AspectScore 0.2240 FolkRank 0.2136 InteliScore 0.1801 Popularity 0.0937 KOM – Multimedia Communications Lab 28
  • Evaluation Results for LeaveRTOutEvaluation results for the recommendation task having tag as input KOM – Multimedia Communications Lab 29
  • Evaluation Results for LeaveRTOutEvaluation results for the recommendation task having tag as input Approaches MAP Popularity 0.0834 AspectScore 0.0589 FolkRank 0.0529 InteliScore 0.0433 KOM – Multimedia Communications Lab 30
  • Conclusion and Future WorkExploiting semantic information for resource ranking in folksonomies AspectScore InteliScore Tag disambiguation & importance of Based on semantic tags (based on type) n relatedness between tags Perso Typ e Loca tion e.g. XESA Topic Event Oth Act er ivit yLimitations !  Manually labeled tag type dataset – error prone, subjective !  XESA based on English Wikipedia – No semantic relatedness measurable for 27% of tags in corpusFuture Work !  Evaluation using CROKODIL corpus – an e-learning application with tag types !  User Study www.crokodil.de KOM – Multimedia Communications Lab 31
  • Questions & Contact KOM – Multimedia Communications Lab 32