
67ecbea2d67f67df60712f536f0f7c22.ppt
- Количество слайдов: 37
Lehrstuhl für Angewandte Informatik in den Kultur-, Geschichts- und Geowissenschaften Otto-Friedrich-Universität Bamberg Modelling Collaborative Semantics with a Geographic Recommender Christoph Schlieder Se. Co. GIS Workshop November 7, 2007, Auckland
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing A geographic place Bamberg UNESCO world heritage site Schlieder: Modelling Collaborative Semantics 08 -2
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing A different conceptualization Bamberg beer capital of Bavaria Schlieder: Modelling Collaborative Semantics 08 -3
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing daily. elsch. eu Yet another conceptualization Bamberg ? Schlieder: Modelling Collaborative Semantics 08 -4
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Conceptual modelling n. Place concepts } „Bamberg“, „Southern Germany“, „Europe“, … } Thematically and spatially different conceptualizations n. Issues } Formal semantics of place concepts } Data about different conceptualizations n. Contributions } Semantic analysis based on multi-object (!) tagging } User similarity data from a geographic recommender Schlieder: Modelling Collaborative Semantics 08 -5
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Tripost Recommender Schlieder: Modelling Collaborative Semantics 08 -6
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Part 1 Geo-information communities Part 2 Collaborative Semantics Part 3 Geographic Recommender Schlieder: Modelling Collaborative Semantics 08 -7
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Geo-information communities n. Information community } Gould & Hecht (2001) A Framework for Geospatial and Statistical Information OGC white paper An information community is a group of people who share a common geospatial feature data dictionary (including definitions of feature relationships) and a common metadata schema. Gould & Hecht (2001) Schlieder: Modelling Collaborative Semantics 08 -8
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Example n. Cadastral Communities } Data and process models } 27 national cadastral authorities in the EU } 1 community designing the Cadastral Reference Model n. Ontological engineering } One ontology per information community Schlieder: Modelling Collaborative Semantics Cadastral Reference Model Lemmen et al. (2003) 08 -9
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Conceptual modelling n. High quality } 30 experts from cadastral agencies, GIScience and Knowledge Engineering } Description logic-based modelling (OWL-DL) n. High cost } 4 years for understanding and modelling property transaction processes Schlieder: Modelling Collaborative Semantics COST G 9 Modelling real property transactions 08 -10
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Ontological engineering Core Cadastral Data Model + conformity constraints Conformity checker (OWL-DL) Hess, Schlieder (2006) Ontology-based Verification of Core Model Conformity, CEUS National cadastral data model + intended correspondences Schlieder: Modelling Collaborative Semantics 08 -11
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Information communities n. Traditional view } Each information community defines its ontology } Number of communities or ontologies << 100 } Complex conceptualization uses DL role restrictions Schlieder: Modelling Collaborative Semantics n. Semantic boundaries } Ontologies come with crisp semantic boundaries } The Greek cadastral model is not the Danish model } Semantic Web technologies are appropriate (OWL-DL) 08 -12
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Part 1 Geo-information communities Part 2 Collaborative Semantics Part 3 Geographic Recommender Schlieder: Modelling Collaborative Semantics 08 -13
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Collaborative geodata acquisition www. openstreetmap. org n. Social Web } Communities of users who collect geospatial data n. Collaborative mapping dense data for London www. openstreetmap. org } GPS biking trail libraries Morris et al. (2004), Matyas (2007) } Public domain street maps www. openstreetmap. org sparse data for Brussels Schlieder: Modelling Collaborative Semantics 08 -14
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Collaborative metadata acquisition n. Social tagging } Categorization of geospatial data by a community } Keywords („tags“) describe spatio-temporal coverage and content type n. Folksonomies } folk taxonomy = tag vocabulary Schlieder: Modelling Collaborative Semantics www. geograph. org. uk 08 -15
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Tagging as categorization task tagged by data producer farm track Schlieder: Modelling Collaborative Semantics 08 -16
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Tag frequency n. Example } 422. 895 images } 2. 784 categories (tags) n. Power law } frequency rank - } 36% tags used once only 24% tags used 2 -5 times } Most frequent tag used 17. 360 times rank tag 1 Church 2 Farmland 3 Farm … 2782 Windmill stump 2783 Luminous object in space (sun) 2784 Penstock www. geograph. org. uk Schlieder: Modelling Collaborative Semantics 08 -17
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing www. panoramio. com/photo/201427 Spatial coverage Neuschwanstein POI in Google maps Schlieder: Modelling Collaborative Semantics 08 -18
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Folksonomies n. Low cost } Categorization by voluntary contributors (non-experts) n. Low quality } No controlled vocabulary house vs. house manson vs. manor house } misclassifications Misclassification by a non-expert Schlieder: Modelling Collaborative Semantics 08 -19
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing The semantics of tags n. User tagging } Not just the contributor but all users provide tags } Conflicting tags (!) Classical view } Ternary semantic relation for user tagged data Gruber (2005) n. Semantic analysis Schlieder: Modelling Collaborative Semantics tagging(object, tag) tagging(object, tag, user) 08 -20
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Multi-object tagging Semantic analysis tagging({obj 1, …, obj. N}, tag, user) place name tag Collection of objects Schlieder: Modelling Collaborative Semantics 08 -21
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Bug or feature? n. Quality problem (bug) } Serious for folksonomies } Even more serious if user tagging is permitted } Unmanageable for multiobject user tagging? Schlieder: Modelling Collaborative Semantics n. Consequence } Use folksonomies only as the poor man‘s ontology 08 -22
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Bug or feature? n. Data source (feature) } Multi-object user tagging informs us about different conceptualizations Schlieder: Modelling Collaborative Semantics n. Consequence } Invert the task of finding a tag for a multi-object } Find n objects from a collection of m >> n to illustrate a (place) concept 08 -23
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing The semantics of multi-object tags n. Hypothesis } Selection is based on two conflicting criteria } Typicality: choose typical instances of the concept } Variablity: show the variability of the concept violation of the variability criterion Schlieder: Modelling Collaborative Semantics 08 -24
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Empirical data Schlieder: Modelling Collaborative Semantics 08 -25
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Conceptual modelling n Issues } How can we describe the semantics of place concepts? } How do we obtain data about different conceptualizations? n Selection task } Selection seems based on two conflictin criteria: typicality and variability n Multi-object tagging } User tagging of multi-objects informs about the place concepts of individual users } tagging({obj 1, …, obj. N}, tag, user) Schlieder: Modelling Collaborative Semantics 08 -26
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Part 1 Geo-information communities Part 2 Collaborative Semantics Part 3 Geographic Recommender Schlieder: Modelling Collaborative Semantics 08 -27
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Recommender systems Item-to-item similarity recommendations www. amazon. com Schlieder: Modelling Collaborative Semantics 08 -28
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Multi-object recommendation n. Use case } The user selects images and captions for a patchwork postcard. } The system generates other patchwork postcards with appropriate captions } www. wiai. unibamberg. de/tripost Schlieder: Modelling Collaborative Semantics Tri. Post Webservice 08 -29
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Tags of a single user Anna‘s multi-object tags Antwerpen Bamberg Cardiff Dublin Schlieder: Modelling Collaborative Semantics 08 -30
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Feature similarity Anna Bamberg Bill Clio Don 2 -4 -5 1 -4 -6 2 -3 -5 1 -4 -6 2 -4 -6 1 -4 -5 1 -2 -3 1 -3 -6 4 -5 -6 1 -2 -3 2 -5 -6 1 -3 -6 Cardiff Southern Germany 1 -2 -6 2 -4 -6 3 -5 -6 Southeast of England 2 -4 -5 2 -5 -6 1 -3 -5 Emma Franz 2 -3 -4 sim(A, B) = |A∩B| / |A∪B| 2/3 0. 66 Schlieder: Modelling Collaborative Semantics 08 -31
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing User-to-user similarity Anna Clio Don Emma Franz . 66 Anna Bill . 22 . 66 . 33 . 66 . 22 . 33 . 44 . 77 . 55 . 66 . 42 . 33 . 55 Bill . 66 Clio . 22 Don . 66 . 33 . 55 Emma . 33 . 44 . 66 . 33 Franz . 66 . 77 . 42 . 55 Schlieder: Modelling Collaborative Semantics . 33 08 -32
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Spatial similarity n. Spatial Partonomy } Users visiting a similar selection of places are considered similar } Example: Europe in 7 days Which Countries? Which Cities? Which Fotographs? Printed patchwork postcard Schlieder: Modelling Collaborative Semantics 08 -33
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Computing similarity n. Measures } Feature similarity e. g. Tversky measure } User-user similarity e. g. averaged feature similarity n. Central idea } User-to-user similarity in the selection task is interpreted as a measure for shared conceptualization n. Information community } The community of a user u consists of the k users most similar to u. Schlieder: Modelling Collaborative Semantics 08 -34
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Tag Communities Fuzzy semantic boundary 2 -, 3 -, 4 -community? A B A E E B E A B D D C F C D F F C F 3 -neighbors(C) Schlieder: Modelling Collaborative Semantics C 3 -neighbors(F) 08 -35
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Conclusions n. Issues } Formal semantics of place concepts } Data about different conceptualizations n. Contributions } Semantic analysis based on multi-object (!) tagging } User similarity data from a geographic recommender n. Consequences } Tagging communities are different from information communities Schlieder: Modelling Collaborative Semantics 08 -36
Chair of Computing in the Cultural Sciences Laboratory for Semantic Information Processing Conclusions n. Folksonomies } modeling of semantics before the emergence of information communities } before crisp semantic boundaries have been established n. Semantic Web ontologies } modeling of semantics after that phase } they assume crisp semantic boundaries Schlieder: Modelling Collaborative Semantics 08 -37