Most automated hate speech detection models rely on human annotations for training and evaluation. Logic and research indicate that people who belong to groups targeted by hate speech are better at identifying it, often due to their increased familiarity with the topic and associated hate speech terminology. However, most hate speech annotation practices overlook this issue, and hence the labels produced tend to have a reduced accuracy. In this paper, we describe an approach where the text to be annotated is supplemented with background semantics, to expose the meaning of hate speech terminology that is less likely to be known to general annotators. We test the impact of this approach by measuring change in inter-annotator agreement, before and after introducing semantics, between two groups of annotators; those who belong to the target group of hate speech, and those who are not. Our experiments show that infusing text with semantic background increases inter-annotator agreement by up to 11.3% on average, aligning the annotations from annotators who do not belong to the target groups with those from the target groups.

Misinformation has a pervasive thread running through society, causing confusion, mistrust, and uncertainty. The detection, tracking, and countering of misinformation is a very active research area with an intense need for data about circulating claims and their attributes, fact-checks, and verification outcomes. Although various relevant datasets exist, they tend to be of limited scope in terms of time coverage, topics, country, language, and quantity. In this paper, we introduce CimpleKG as an open and continuously updated semantic resource. CimpleKG links daily updated data from 77 fact-checking organisations with over 217k documents from static misinformation datasets. The knowledge graph is also augmented with relevant textual features and entities extracted from the textual data integrated into the graph. At the time of writing, the knowledge graph contains more than 15m triples, including 263k+ distinct entities and 1m textual features with over 203k fact-checked claims, spanning 26 languages and 36 countries. CimpleKG is publicly available and has been used in various research studies and web applications. Resource Type: Knowledge Graph. License: CC BY-NC-SA 4.0. SPARQL Endpoint: https://purl.org/net/cimplekg/sparql . KG Releases: https://purl.org/net/cimplekg/knowledge-graph . KG Explorer: https://purl.org/net/cimplekg/explorer .

Online threats to children, in the form of cyberbullying, grooming, and sexting, have reached unprecedented and alarming levels. Support is still lacking despite endless efforts by child safety organisations and online safety educational programmes. This is mainly due to children feeling apprehensive in such situations, ashamed of revealing their distressing encounter to an adult or even for not having anyone to approach with their concerns. This paper investigates how children envision the potential support of a chatbot in such contexts. We captured design requirements for such a chatbot through a participatory design approach involving 110 schoolchildren in the UK. Using LEGO figures, they elaborated and performed stories featuring the interaction of a child under threat with a chatbot. The analysis of the dialogues in their performances and their reflections resulted in a set of expected tasks for the chatbot, a conversation flow, and novel socio-technical requirements addressing potential users’ main concerns and expectations.

This paper summarises work where we combined semantic web technologies with deep learning systems to obtain state-of-the art explainable misinformation detection. We proposed a conceptual and computational model to describe a wide range of misinformation detection systems based around the concepts of credibility and reviews. We described how Credibility Reviews (CRs) can be used to build networks of distributed bots that collaborate for misinformation detection which we evaluated by building a prototype based on publicly available datasets and deep learning models.

In this paper, we present electronic participatory budgeting (ePB) as a novel application domain for recommender systems. On public data from the ePB platforms of three major US cities - Cambridge, Miami and New York City-, we evaluate various methods that exploit heterogeneous sources and models of user preferences to provide personalized recommendations of citizen proposals. We show that depending on characteristics of the cities and their participatory processes, particular methods are more effective than others for each city. This result, together with open issues identified in the paper, call for further research in the area.

Social media is a common place for people to post and share digital reflections of their life events, including major events such as getting married, having children, graduating, etc. Although the creation of such posts is straightforward, the identification of events on online media remains a challenge. Much research in recent years focused on extracting major events from Twitter, such as earthquakes, storms, and floods. This paper however, targets the automatic detection of personal life events, focusing on five events that psychologists found to be the most prominent in people lives. We define a variety of features (user, content, semantic and interaction) to capture the characteristics of those life events and present the results of several classification methods to automatically identify these events in Twitter. Our proposed classification methods obtain results between 0.84 and 0.92 F1-measure for the different types of life events. A novel contribution of this work also lies in a new corpus of tweets, which has been annotated by using crowdsourcing and that constitutes, to the best of our knowledge, the first publicly available dataset for the automatic identification of personal life events from Twitter.

Large medical conferences offer opportunities for participants to find industry exhibitors that offer products and services relevant to their professional interests. Companies often invest significant effort in promotions that encourage participants to spend time at their stand (e.g. providing free gifts, leaflets, running competitions) and register some contact details. Attendees will use the conference to find others who also share similar professional interests, as well as keep up to date with developments on products such has pharmaceuticals and medical equipment. From both perspectives, a number of improvements can be made to enhance the overall experience by using existing active RFID technology: Vendors would be able to more closely monitor the success of their promotions with statistics on the stand's visitors, as well as find more potential customers by using real-time visualizations; Participants would be able to log their social interactions, keeping an electronic history of the people they have met. The SocioPatterns project and Live Social Semantics experiments have recently demonstrated a scalable and robust infrastructure that would support these kinds of improvements. In this paper, we propose an infrastructure that provides enhanced social interaction services for vendors and participants by using small active RFID badges worn by attendees and attached to fixed locations.

Social interactions are one of the key factors to the success of conferences and similar community gatherings. This paper describes a novel application that integrates data from the semantic web, online social networks, and a real-world contact sensing platform. This application was successfully deployed at ESWC09, and actively used by 139 people. Personal profiles of the participants were automatically generated using several Web 2.0 systems and semantic academic data sources, and integrated in real-time with face-to-face contact networks derived from wearable sensors. Integration of all these heterogeneous data layers made it possible to offer various services to conference attendees to enhance their social experience such as visualisation of contact data, and a site to explore and connect with other participants. This paper describes the architecture of the application, the services we provided, and the results we achieved in this deployment. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

As more ontologies become publicly available, finding the "right" ontologies becomes much harder. In this paper, we address the problem of ontology search: finding a collection of ontologies from an ontology repository that are relevant to the user's query. In particular, we look at the case when users search for ontologies relevant to a particular topic (e.g., an ontology about anatomy). Ontologies that are most relevant to such query often do not have the query term in the names of their concepts (e.g., the Foundational Model of Anatomy ontology does not have the term "anatomy" in any of its concepts' names). Thus, we present a new ontology-search technique that helps users in these types of searches. When looking for ontologies on a particular topic (e.g., anatomy), we retrieve from the Web a collection of terms that represent the given domain (e.g., terms such as body, brain, skin, etc. for anatomy). We then use these terms to expand the user query. We evaluate our algorithm on queries for topics in the biomedical domain against a repository of biomedical ontologies. We use the results obtained from experts in the biomedical-ontology domain as the gold standard. Our experiments demonstrate that using our method for query expansion improves retrieval results by a 113%, compared to the tools that search only for the user query terms and consider only class and property names (like Swoogle). We show 43% improvement for the case where not only class and property names but also property values are taken into account.

One of the main hurdles towards a wide endorsement of ontologies is the high cost of constructing them. Reuse of existing ontologies offers a much cheaper alternative than building new ones from scratch, yet tools to support such reuse are still in their infancy. However, more ontologies are becoming available on the web, and online libraries for storing and indexing ontologies are increasing in number and demand. Search engines have also started to appear, to facilitate search and retrieval of online ontologies. This paper presents a fresh view on constructing ontologies automatically, by identifying, ranking, and merging fragments of online ontologies.

In view of the need to provide tools to facilitate the re-use of existing knowledge structures such as ontologies, we present in this paper a system, AKTiveRank, for the ranking of ontologies. AKTiveRank uses as input the search terms provided by a knowledge engineer and, using the output of an ontology search engine, ranks the ontologies. We apply a number of metrics in an attempt to investigate their appropriateness for ranking ontologies, and compare the results with a questionnaire-based human study. Our results show that AKTiveRank will have great utility although there is potential for improvement.

Gazeteers and geographical thesauri can be regarded as parsimonious spatial models that associate geographical location with place names and encode some semantic relations between the names. They are of particular value in processing information retrieval requests in which the user employs place names to specify geographical context. Typically the geometric locational data in a gazetteer are confined to a simple footprint in the form of a centroid or a minimum bounding rectangle, both of which can be used to link to a map but are of limited value in determining spatial relationships. Here we describe a Voronoi diagram method for generating approximate regional extents from sets of centroids that are respectively inside and external to a region. The resulting approximations provide measures of areal extent and can be used to assist in answering geographical queries by evaluating spatial relationships such as distance, direction and common boundary length. Preliminary experimental evaluations of the method have been performed in the context of a semantic modelling system that combines the centroid data with hierarchical and adjacency relations between the associated place names.