Urban Problem LOD for Understanding the Problem Structure and Detecting Vicious Cycles

Urban problems, such as littering, graffiti, and homelessness have various causes and are linked to each other; thus, understanding of the problem structure is required for detecting and solving root problems that generate vicious cycles of the problems. Moreover, in order to implement the action plans for solving these problems, local governments need to estimate the cost-effectiveness of the plans. Therefore, this paper proposes constructing Urban Problem Linked Open Data (UPLOD) that include urban problems' causality and the related cost information of their budget sheets. We first design an RDF schema that represents the urban problems' causality and then we extend the schema to include budget information based on RDF Data Cube Vocabulary. Next, we instantiate actual causes and effects using crowdsourcing supporting with natural language processing based techniques. In addition, we complement the UPLOD by inferring with Semantic Web Rule Language (SWRL) rules. Finally, we detect several root problems that lead to the cycle of the problems using SPARQL queries and then confirm the results with evidence manually extracted from articles of local governments.

[1]  Paloma Martínez,et al.  DINTO: Using OWL Ontologies and SWRL Rules to Infer Drug-Drug Interactions and Their Mechanisms , 2015, J. Chem. Inf. Model..

[2]  Jane Hunter,et al.  An ontological approach to dynamic fine-grained Urban Indicators , 2017, ICCS.

[3]  Luis Tari,et al.  Semantic Inference for Pharmacokinetic Drug-Drug Interactions , 2014, 2014 IEEE International Conference on Semantic Computing.

[4]  Craig A. Knoblock,et al.  Using a Knowledge Graph to Combat Human Trafficking , 2015, SEMWEB.

[5]  Luis von Ahn.  Games with a Purpose , 2006, Computer.

[6]  Emanuele Della Valle,et al.  Linking Smart Cities Datasets with Human Computation - The Case of UrbanMatch , 2012, SEMWEB.

[7]  Gianluca Demartini,et al.  Large-scale linked data integration using probabilistic reasoning and crowdsourcing , 2013, The VLDB Journal.

[8]  Jacob Cohen,et al.  The Equivalence of Weighted Kappa and the Intraclass Correlation Coefficient as Measures of Reliability , 1973 .

[9]  William E. Winkler,et al.  The State of Record Linkage and Current Research Problems , 1999 .

[10]  Isabelle Augenstein,et al.  LODifier: Generating Linked Data from Unstructured Text , 2012, ESWC.

[11]  Toramatsu Shintani,et al.  Towards Continuous Collaboration on Civic Tech Projects: Use Cases of a Goal Sharing System Based on Linked Open Data , 2015, ePart.

[12]  Yuji Matsumoto,et al.  Japanese Dependency Analysis using Cascaded Chunking , 2002, CoNLL.

[13]  Takahiro Kawamura,et al.  Linked Urban Open Data Including Social Problems' Causality and Their Costs , 2017, JIST.

[14]  Ian H. Witten,et al.  Learning to link with wikipedia , 2008, CIKM '08.

[15]  A. Viera,et al.  Understanding interobserver agreement: the kappa statistic. , 2005, Family medicine.

[16]  Takahiro Kawamura,et al.  Building Urban LOD for Solving Illegally Parked Bicycles in Tokyo , 2016, International Semantic Web Conference.

[17]  Lorena Etcheverry,et al.  Modeling and Querying Data Warehouses on the Semantic Web Using QB4OLAP , 2014, DaWaK.

[18]  Jens Lehmann,et al.  Test-driven evaluation of linked data quality , 2014, WWW.

[19]  Deborah L. McGuinness,et al.  From Data to City Indicators: A Knowledge Graph for Supporting Automatic Generation of Dashboards , 2017, ESWC.

[20]  Umberto Straccia,et al.  Fuzzy Ontology Representation using OWL 2 , 2010, Int. J. Approx. Reason..

[21]  Jens Lehmann,et al.  LinkedSpending: OpenSpending becomes Linked Open Data , 2015, Semantic Web.

[22]  Takahiro Kawamura,et al.  Construction of Linked Urban Problem Data with Causal Relations Using Crowdsourcing , 2017, 2017 6th IIAI International Congress on Advanced Applied Informatics (IIAI-AAI).

[23]  Takahiro Kawamura,et al.  Self-supervised capturing of users' activities from weblogs , 2012, Int. J. Intell. Inf. Database Syst..