Since the textual contents on online social media are highly unstructured, informal, and often misspelled, existing research on message-level offensive language detection cannot accurately detect offensive content. Meanwhile, user-level offensiveness detection seems a more feasible approach but it is an under researched area. To bridge this gap, we propose the Lexical Syntactic Feature (LSF) architecture to detect offensive content and identify potential offensive users in social media. We distinguish the contribution of pejoratives/profanities and obscenities in determining offensive content, and introduce hand-authoring syntactic rules in identifying name-calling harassments. In particular, we incorporate a user's writing style, structure and specific cyber bullying content as features to predict the user's potentiality to send out offensive content. Results from experiments showed that our LSF framework performed significantly better than existing methods in offensive content detection. It achieves precision of 98.24% and recall of 94.34% in sentence offensive detection, as well as precision of 77.9% and recall of 77.8% in user offensive detection. Meanwhile, the processing speed of LSF is approximately 10msec per sentence, suggesting the potential for effective deployment in social media.

/pdf/detecting-offensive-language-in-social-media-to-protect-3eovt2hnep.pdf

Detecting Offensive Language in Social Media to Protect Adolescent Online Safety

Cultural Heritage (CH) data is syntactically and semantically heterogeneous, multilingual, semantically rich, and highly interlinked. It is produced in a distributed, open fashion by museums, libraries, archives, and media organizations, as well as individual persons. Managing publication of such richness and variety of content on the Web, and at the same time supporting distributed, interoperable content creation processes, poses challenges where traditional publication approaches need to be re-thought. Application of the principles and technologies of Linked Data and the Semantic Web is a new, promising approach to address these problems. This development is leading to the creation of large national and international CH portals, such as Europeana, to large open data repositories, such as the Linked Open Data Cloud, and massive publications of linked library data in the U.S., Europe, and Asia. Cultural Heritage has become one of the most successful application domains of Linked Data nd Semantic Web technologies. This book gives an overview on why, when, and how Linked (Open) Data and Semantic Web technologies can be employed in practice in publishing CH collections and other content on the Web. The text first motivates and presents a general semantic portal model and publishing framework as a solution approach to distributed semantic content creation, based on an ontology infrastructure. On the Semantic Web, such an infrastructure includes shared metadata models, ontologies, and logical reasoning, and is supported by shared ontology and other Web services alleviating the use of the new technology and linked data in legacy cataloging systems. The goal of all this is to provide layman users and researchers with new, more intelligent and usable Web applications that can be utilized by other Web applications, too, via well-defined Application Programming Interfaces (API). At the same time, it is possible to provide publishing organizations with more cost-efficient so utions for content creation and publication. This book is targeted to computer scientists, museum curators, librarians, archivists, and other CH professionals interested in Linked Data and CH applications on the Semantic Web. The text is focused on practice and applications, making it suitable to students, researchers, and practitioners developing Web services and applications of CH, as well as to CH managers willing to understand the technical issues and challenges involved in linked data publication. Table of Contents: Cultural Heritage on the Semantic Web / Portal Model for Collaborative CH Publishing / Requirements for Publishing Linked Data / Metadata Schemas / Domain Vocabularies and Ontologies / Logic Rules for Cultural Heritage / Cultural Content Creation / Semantic Services for Human and Machine Users / Conclusions

Publishing and Using Cultural Heritage Linked Data on the Semantic Web

This paper presents the vision and results of creating a national level cross-domain ontology and ontology service infrastructure in Finland. The novelty of the infrastructure is based on two ideas. First, a system of open source core ontologies is being developed by transforming thesauri into mutually aligned lightweight ontologies, including a large top ontology that is extended by various domain specific ontologies. Second, the ONKI Ontology Server framework for publishing ontologies as ready to use services has been designed and implemented. ONKI provides legacy and other applications with ready to use functionalities for using ontologies on the HTML level by Ajax and semantic widgets. The idea is to use ONKI for creating mash-up applications in a way analogous to using Google or Yahoo Maps, but in our case external applications are mashed-up with ontology support.

/pdf/building-a-national-semantic-web-ontology-and-ontology-3mbrhacozu.pdf

Building a national semantic web ontology and ontology service infrastructure the FinnONTO approach

A linguistic analysis of grooming strategies of online child sex offenders: Implications for our understanding of predatory sexual behavior in an increasingly computer-mediated world

Resolving location expressions in text to the correct physical location, also known as geocoding or grounding, is complicated by the fact that so many places around the world share the same name. Correct resolution is made even more difficult when there is little context to determine which place is intended, as in a 140-character Twitter message, or when location cues from different sources conflict, as may be the case among different metadata fields of a Twitter message. We used supervised machine learning to weigh the different fields of the Twitter message and the features of a world gazetteer to create a model that will prefer the correct gazetteer candidate to resolve the extracted expression. We evaluated our model using the F1 measure and compared it to similar algorithms. Our method achieved results higher than state-of-the-art competitors.

/pdf/geocoding-location-expressions-in-twitter-messages-a-1uhswcoi36.pdf

Geocoding location expressions in Twitter messages: A preference learning method

This article presents the vision and results of creating the basis for a national semantic Web content infrastructure in Finland in 2003-2007. The main elements of the infrastructure are shared and open metadata schemas, core ontologies, and public ontology services. Several practical applications testing and demonstrating the usefulness of the infrastructure are overviewed in the fields of eculture, ehealth, egovernment, elearning, and ecommerce.

/pdf/elements-of-a-national-semanticweb-infrastructure-case-study-2bqfvaeqcv.pdf

Elements of a National SemanticWeb Infrastructure--Case Study Finland on the Semantic Web

Geographic place names are semantically often highly ambiguous. For example, there are 491 places in Finland sharing the same name ”Isosaari” (great island) that are instances of several geographical classes, such as Island, Forest, Peninsula, Inhabited area, etc. Referencing unambiguously to a particular ”Isosaari”, either when annotating content or during information retrieval, can be quite problematic and requires usage of advanced search methods and maps for semantic disambiguation. Historical places introduce even more challenges, since historical metadata commonly make spatiotemporal references to historical regions and places using names whose meanings are non-existing or different in different times. This paper presents how these problems have been addressed in a large Finnish place ontology SUO and a historical geo-ontology SAPO. A location ontology server ONKI-Geo has been created for publishing the ontologies and utilizing them as mashup services. To demonstrate the usability of our ontologies, two case applications in the cultural heritage domain are presented.

/pdf/ontology-based-disambiguation-of-spatiotemporal-locations-1hmg4vh12n.pdf

Ontology-based disambiguation of spatiotemporal locations

Geographic knowledge is essential in handling a large variety of resources, including cultural contents such as museum artifacts, maps, books, photographs, and videos. The metadata of such resources often need to refer to a geographic entity or region, for example to the place where an artifact was produced, used, or found. In this paper, we examine how geographical knowledge may be represented ontologically to enable different types of searches, visualization, and inference in cultural semantic portals and other semantic geo-applications. In particular, we show how change in time between historical regions can be explicated as an ontology and be used for reasoning. Regarding search and visualization, we show how maps of different time periods can be visualized as transparent overlays on top of Google Maps, how cultural content can be visualized on them, how geo-based queries can be formulated based on maps, and how additional services, such as a meta-search system, can be integrated in the mash-up system. The work presented is being integrated at the practical level in the cultural semantic cross-domain portal CultureSampo.

/pdf/ontology-based-modeling-and-visualization-of-cultural-spatio-3v1bk8o8q1.pdf

Ontology-based Modeling and Visualization of Cultural Spatio-temporal Knowledge

Geographic place names are widely used but are semantically often highly ambiguous. For example, there are 491 places in Finland sharing the same name “Isosaari” (great island) that are instances of several geographical classes, such as Island, Forest, Peninsula, Inhabited area, etc. Referencing unambiguously to a particular “Isosaari”, either when annotating content or during information retrieval, can be quite problematic and requires usage of advanced search methods and maps for semantic disambiguation. This paper presents an ontology server, ONKI-Paikka, for solving the place finding and place name disambiguation problem. In ONKI-Paikka, places can be found by a faceted search engine, combined with semantic autocompletion and a map service for constraining search and for visualizing results. The service can be connected to legacy applications cost-effectively by using Ajax-technology in the same spirit as Google Maps that is used in ONKI-Paikka as a subservice. 1 SUO Place Ontology ONKI-Paikka is based on the Finnish Place Ontology SUO [2] being developed as a part of the national semantic web infrastructure in Finland [1]. The SUO has been populated with 1) place information from the Geographic Names Register (GNR) provided by the National Land Survey of Finland and with 2) place information from the GEOnet Names Server (GNS) maintained by the National Geospatial-Intelligence Agency (NGA) and the U.S. Board on Geographic Names (US BGN). GNR contains about 800,000 names of natural and man-made features in Finland, including data such as place type or feature type and the coordinates of a place. The GNS register contains similar information of about 4,100,000 places around the world excluding places in the United States. 2 ONKI-Paikka Ontology Service ONKI-Paikka publishes SUO with online ontology services for humans and machines to use. The user interface utilizes Ajax-techniques for communicating with the ONKI-Paikka database server containing the place instances. The place 1 Operational at http://demo.seco.tkk.fi/onkipaikka/ 2 http://www.maanmittauslaitos.fi/ 3 http://earth-info.nga.mil/gns/html/ 4 http://ajax.org/ finder contains a simple faceted search engine for narrowing the search along the following dimensions: 1) Place name facet filters matching place instances using string autocompletion for their labels. 2) Place type facet of place types (City, Island, Cemetery, etc.) is used to focus search to places of desired types. 3) Language facet limits search to place names in given languages (Finnish, Swedish, English, and three dialects of Sami). 4) Time facet is used to focus search on historical place names. 5) Map facet allows the user to specify a polygon area in which to search for the place on the map [2]. The polygon functions as a narrowing criteria for the search in the same way as category selections in the other facets. 6) Area facet makes it possible to focus search on continents, countries, and their smaller regions. By using ONKI-Paikka one can e.g. find easily on the map all places of 1) some type with 2) names beginning with some letters, and that are 3) inside a polygon out of millions of resources. ONKI-Paikka uses Google Maps API 5 for visualization, and can be connected to and utilized in legacy systems using Ajax and mash-up techniques. In a museum cataloging system, for example, places can be found by using the ONKI-Paikka user interface and by pushing the “Select” button, the corresponding URI or coordinates are transferred from the centralized national service into the lecagy application. ONKI-Paikka is an instance of the ONKI ontology service framework being built in Finland [1]. A technical challenge with the ONKI-Paikka service is the large size of the SUO. The response times of the faceted search were several minutes when using a straight-forward Jena implementation. To solve the efficiency problem, only the SUO ontology classes, without the instances, are stored in a Jena model, and a separate indexing layer was created for the millions of instances. The indexing of the instances is created in a relational database (MySQL) making complex combinational searches possible and relatively fast.

/pdf/an-ontology-service-for-geographical-content-zrbc1a5mac.pdf

An ontology service for geographical content

The process of spatial data quality evaluation is a set of interrelated activities aiming to produce a data quality result, and moreover, to fulfil the quality requirements set forth by the customers. The quality evaluation must be done in a consistent manner in order to determine whether the achieved quality level meets the requirements, and also to be able to compare the quality results between different datasets. Quality assurance and evaluation are integral parts of the dataset production. There exist several quality standards that should be taken into account in the production process. However, it is not always clear how to adopt the standards in practice. The goal of this paper is to offer an ontological framework for the construction of the spatial data quality evaluation process, which will correspond to the domain knowledge and the process workflow presented in the quality standards for geographic information. In this paper, we define the different process perspectives needed to capture the knowledge related to the spatial data quality evaluation process. Furthermore, we present a partial domain ontology for the spatial data quality and quality evaluation process. Since the ontology makes explicit the conceptualizations behind the terminologies and process models presented in the standards, it can facilitate, among other things, the implementation of the standards in practice, and could thus have an active role in standardization and quality harmonization efforts.

/pdf/an-ontology-driven-approach-for-spatial-data-quality-2g04jdwygg.pdf

Riikka Henriksson

Papers

Elements of a National SemanticWeb Infrastructure--Case Study Finland on the Semantic Web

Ontology-based disambiguation of spatiotemporal locations

Ontology-based Modeling and Visualization of Cultural Spatio-temporal Knowledge

An ontology service for geographical content

An Ontology-driven Approach for Spatial Data Quality Evaluation