Martin Glauer, A. Memariani, F. Neuhaus, T. Mossakowski, Janna Hastings
Reference ontologies provide a shared vocabulary and knowledge resource for their domain. Manual construction and annotation enables them to maintain high quality, allowing them to be widely accepted across their community. However, the manual ontology development process does not scale for large domains. We present a new methodology for automatic ontology extension for domains in which the ontology classes have associated graph-structured annotations, and apply it to the ChEBI ontology, a prominent reference ontology for life sciences chemistry. We train Transformer-based deep learning models on the leaf node structures from the ChEBI ontology and the classes to which they belong. The models are then able to automatically classify previously unseen chemical structures, resulting in automated ontology extension. The proposed models achieved an overall F1 scores of 0.80 and above, improvements of at least 6 percentage points over our previous results on the same dataset. In addition, the models are interpretable: we illustrate that visualizing the model’s attention weights can help to explain the results by providing insight into how the model made its decisions. We also analyse the performance for molecules that have not been part of the ontology and evaluate the logical correctness of the resulting extension.
{"title":"Interpretable ontology extension in chemistry","authors":"Martin Glauer, A. Memariani, F. Neuhaus, T. Mossakowski, Janna Hastings","doi":"10.3233/sw-233183","DOIUrl":"https://doi.org/10.3233/sw-233183","url":null,"abstract":"Reference ontologies provide a shared vocabulary and knowledge resource for their domain. Manual construction and annotation enables them to maintain high quality, allowing them to be widely accepted across their community. However, the manual ontology development process does not scale for large domains. We present a new methodology for automatic ontology extension for domains in which the ontology classes have associated graph-structured annotations, and apply it to the ChEBI ontology, a prominent reference ontology for life sciences chemistry. We train Transformer-based deep learning models on the leaf node structures from the ChEBI ontology and the classes to which they belong. The models are then able to automatically classify previously unseen chemical structures, resulting in automated ontology extension. The proposed models achieved an overall F1 scores of 0.80 and above, improvements of at least 6 percentage points over our previous results on the same dataset. In addition, the models are interpretable: we illustrate that visualizing the model’s attention weights can help to explain the results by providing insight into how the model made its decisions. We also analyse the performance for molecules that have not been part of the ontology and evaluate the logical correctness of the resulting extension.","PeriodicalId":48694,"journal":{"name":"Semantic Web","volume":"4 1","pages":""},"PeriodicalIF":3.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87249569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dimitris Zeginis, E. Kalampokis, Raúl Palma, R. Atkinson, K. Tarabanis
At the domains of agriculture and livestock farming a large amount of data are produced through numerous heterogeneous sources including sensor data, weather/climate data, statistical and government data, drone/satellite imagery, video, and maps. This plethora of data can be used at precision agriculture and precision livestock farming in order to provide predictive insights in farming operations, drive real-time operational decisions, redesign business processes and support policy-making. The predictive power of the data can be further boosted if data from diverse sources are integrated and processed together, thus providing more unexplored insights. However, the exploitation and integration of data used in precision agriculture is not straightforward since they: i) cannot be easily discovered across the numerous heterogeneous sources and ii) use different structural and naming conventions hindering their interoperability. The aim of this paper is to: i) study the characteristics of data used in precision agriculture & livestock farming and ii) study the user requirements related to data modeling and processing from nine real cases at the agriculture, livestock farming and aquaculture domains and iii) propose a semantic meta-model that is based on W3C standards (DCAT, PROV-O and QB vocabulary) in order to enable the definition of metadata that facilitate the discovery, exploration, integration and accessing of data in the domain.
{"title":"A semantic meta-model for data integration and exploitation in precision agriculture and livestock farming","authors":"Dimitris Zeginis, E. Kalampokis, Raúl Palma, R. Atkinson, K. Tarabanis","doi":"10.3233/sw-233156","DOIUrl":"https://doi.org/10.3233/sw-233156","url":null,"abstract":"At the domains of agriculture and livestock farming a large amount of data are produced through numerous heterogeneous sources including sensor data, weather/climate data, statistical and government data, drone/satellite imagery, video, and maps. This plethora of data can be used at precision agriculture and precision livestock farming in order to provide predictive insights in farming operations, drive real-time operational decisions, redesign business processes and support policy-making. The predictive power of the data can be further boosted if data from diverse sources are integrated and processed together, thus providing more unexplored insights. However, the exploitation and integration of data used in precision agriculture is not straightforward since they: i) cannot be easily discovered across the numerous heterogeneous sources and ii) use different structural and naming conventions hindering their interoperability. The aim of this paper is to: i) study the characteristics of data used in precision agriculture & livestock farming and ii) study the user requirements related to data modeling and processing from nine real cases at the agriculture, livestock farming and aquaculture domains and iii) propose a semantic meta-model that is based on W3C standards (DCAT, PROV-O and QB vocabulary) in order to enable the definition of metadata that facilitate the discovery, exploration, integration and accessing of data in the domain.","PeriodicalId":48694,"journal":{"name":"Semantic Web","volume":"41 1","pages":""},"PeriodicalIF":3.0,"publicationDate":"2023-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84050345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Special issue on Semantic Web Meets Health Data Management","authors":"K. Stefanidis, H. Kondylakis, P. Rao","doi":"10.3233/sw-239000","DOIUrl":"https://doi.org/10.3233/sw-239000","url":null,"abstract":"data framework: approach and study”","PeriodicalId":48694,"journal":{"name":"Semantic Web","volume":"49 1","pages":"785-786"},"PeriodicalIF":3.0,"publicationDate":"2023-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89304618","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Rojas, Harm Delva, Pieter Colpaert, R. Verborgh
Publishing transport data on the Web for consumption by others poses several challenges for data publishers. In addition to planned schedules, access to live schedule updates (e.g. delays or cancellations) and historical data is fundamental to enable reliable applications and to support machine learning use cases. However publishing such dynamic data further increases the computational burden for data publishers, resulting in often unavailable historical data and live schedule updates for most public transport networks. In this paper we apply and extend the current Linked Connections approach for static data to also support cost-efficient live and historical public transport data publishing on the Web. Our contributions include (i) a reference specification and system architecture to support cost-efficient publishing of dynamic public transport schedules and historical data; (ii) empirical evaluations on route planning query performance based on data fragmentation size, publishing costs and a comparison with a traditional route planning engine such as OpenTripPlanner; (iii) an analysis of potential correlations of query performance with particular public transport network characteristics such as size, average degree, density, clustering coefficient and average connection duration. Results confirm that fragmentation size influences route planning query performance and converges on an optimal fragment size per network. Size (stops), density and connection duration also show correlation with route planning query performance. Our approach proves to be more cost-efficient and in some cases outperforms OpenTripPlanner when supporting the earliest arrival time route planning use case. Moreover, the cost of publishing live and historical schedules remains in the same order of magnitude for server-side resources compared to publishing planned schedules only. Yet, further optimizations are needed for larger networks (>1000 stops) to be useful in practice. Additional dataset fragmentation strategies (e.g. geospatial) may be studied for designing more scalable and performant Web apis that adapt to particular use cases, not only limited to the public transport domain.
{"title":"Publishing public transport data on the Web with the Linked Connections framework","authors":"J. Rojas, Harm Delva, Pieter Colpaert, R. Verborgh","doi":"10.3233/sw-223116","DOIUrl":"https://doi.org/10.3233/sw-223116","url":null,"abstract":"Publishing transport data on the Web for consumption by others poses several challenges for data publishers. In addition to planned schedules, access to live schedule updates (e.g. delays or cancellations) and historical data is fundamental to enable reliable applications and to support machine learning use cases. However publishing such dynamic data further increases the computational burden for data publishers, resulting in often unavailable historical data and live schedule updates for most public transport networks. In this paper we apply and extend the current Linked Connections approach for static data to also support cost-efficient live and historical public transport data publishing on the Web. Our contributions include (i) a reference specification and system architecture to support cost-efficient publishing of dynamic public transport schedules and historical data; (ii) empirical evaluations on route planning query performance based on data fragmentation size, publishing costs and a comparison with a traditional route planning engine such as OpenTripPlanner; (iii) an analysis of potential correlations of query performance with particular public transport network characteristics such as size, average degree, density, clustering coefficient and average connection duration. Results confirm that fragmentation size influences route planning query performance and converges on an optimal fragment size per network. Size (stops), density and connection duration also show correlation with route planning query performance. Our approach proves to be more cost-efficient and in some cases outperforms OpenTripPlanner when supporting the earliest arrival time route planning use case. Moreover, the cost of publishing live and historical schedules remains in the same order of magnitude for server-side resources compared to publishing planned schedules only. Yet, further optimizations are needed for larger networks (>1000 stops) to be useful in practice. Additional dataset fragmentation strategies (e.g. geospatial) may be studied for designing more scalable and performant Web apis that adapt to particular use cases, not only limited to the public transport domain.","PeriodicalId":48694,"journal":{"name":"Semantic Web","volume":"14 1","pages":"659-693"},"PeriodicalIF":3.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72904415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chang Sun, Marc Gallofré Ocaña, J. V. Soest, M. Dumontier
Developing personal data sharing tools and standards in conformity with data protection regulations is essential to empower citizens to control and share their health data with authorized parties for any purpose they approve. This can be, among others, for primary use in healthcare, or secondary use for research to improve human health and well-being. Ensuring that citizens are able to make fine-grained decisions about how their personal health data can be used and shared will significantly encourage citizens to participate in more health-related research. In this paper, we propose a ciTIzen-centric DatA pLatform (TIDAL) to give individuals ownership of their own data, and connect them with researchers to donate the use of their personal data for research while being in control of the entire data life cycle, including data access, storage and analysis. We recognize that most existing technologies focus on one particular aspect such as personal data storage, or suffer from executing data analysis over a large number of participants, or face challenges of low data quality and insufficient data interoperability. To address these challenges, the TIDAL platform integrates a set of components for requesting subsets of RDF (Resource Description Framework) data stored in personal data vaults based on SOcial LInked Data (Solid) technology and analyzing them in a privacy-preserving manner. We demonstrate the feasibility and efficiency of the TIDAL platform by conducting a set of simulation experiments using three different pod providers (Inrupt, Solidcommunity, Self-hosted Server). On each pod provider, we evaluated the performance of TIDAL by querying and analyzing personal health data with varying scales of participants and configurations. The reasonable total time consumption and a linear correlation between the number of pods and variables on all pod providers show the feasibility and potential to implement and use the TIDAL platform in practice. TIDAL facilitates individuals to access their personal data in a fine-grained manner and to make their own decision on their data. Researchers are able to reach out to individuals and send them digital consent directly for using personal data for health-related research. TIDAL can play an important role to connect citizens, researchers, and data organizations to increase the trust placed by citizens in the processing of personal data.
{"title":"ciTIzen-centric DAta pLatform (TIDAL): Sharing distributed personal data in a privacy-preserving manner for health research","authors":"Chang Sun, Marc Gallofré Ocaña, J. V. Soest, M. Dumontier","doi":"10.3233/sw-223220","DOIUrl":"https://doi.org/10.3233/sw-223220","url":null,"abstract":"Developing personal data sharing tools and standards in conformity with data protection regulations is essential to empower citizens to control and share their health data with authorized parties for any purpose they approve. This can be, among others, for primary use in healthcare, or secondary use for research to improve human health and well-being. Ensuring that citizens are able to make fine-grained decisions about how their personal health data can be used and shared will significantly encourage citizens to participate in more health-related research. In this paper, we propose a ciTIzen-centric DatA pLatform (TIDAL) to give individuals ownership of their own data, and connect them with researchers to donate the use of their personal data for research while being in control of the entire data life cycle, including data access, storage and analysis. We recognize that most existing technologies focus on one particular aspect such as personal data storage, or suffer from executing data analysis over a large number of participants, or face challenges of low data quality and insufficient data interoperability. To address these challenges, the TIDAL platform integrates a set of components for requesting subsets of RDF (Resource Description Framework) data stored in personal data vaults based on SOcial LInked Data (Solid) technology and analyzing them in a privacy-preserving manner. We demonstrate the feasibility and efficiency of the TIDAL platform by conducting a set of simulation experiments using three different pod providers (Inrupt, Solidcommunity, Self-hosted Server). On each pod provider, we evaluated the performance of TIDAL by querying and analyzing personal health data with varying scales of participants and configurations. The reasonable total time consumption and a linear correlation between the number of pods and variables on all pod providers show the feasibility and potential to implement and use the TIDAL platform in practice. TIDAL facilitates individuals to access their personal data in a fine-grained manner and to make their own decision on their data. Researchers are able to reach out to individuals and send them digital consent directly for using personal data for health-related research. TIDAL can play an important role to connect citizens, researchers, and data organizations to increase the trust placed by citizens in the processing of personal data.","PeriodicalId":48694,"journal":{"name":"Semantic Web","volume":"7 1","pages":"977-996"},"PeriodicalIF":3.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78330245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
F. Aisopos, S. Jozashoori, E. Niazmand, Disha Purohit, Ariam Rivas, Ahmad Sakor, Enrique Iglesias, D. Vogiatzis, Ernestina Menasalvas Ruiz, A. R. González, Guillermo Vigueras, Daniel Gómez-Bravo, M. Torrente, Roberto Hernández López, M. P. Pulla, Athanasios Dalianis, A. Triantafillou, G. Paliouras, M. Vidal
Tailoring personalized treatments demands the analysis of a patient’s characteristics, which may be scattered over a wide variety of sources. These features include family history, life habits, comorbidities, and potential treatment side effects. Moreover, the analysis of the services visited the most by a patient before a new diagnosis, as well as the type of requested tests, may uncover patterns that contribute to earlier disease detection and treatment effectiveness. Built on knowledge-driven ecosystems, we devise DE4LungCancer, a health data ecosystem of data sources for lung cancer. In this data ecosystem, knowledge extracted from heterogeneous sources, e.g., clinical records, scientific publications, and pharmacological data, is integrated into knowledge graphs. Ontologies describe the meaning of the combined data, and mapping rules enable the declarative definition of the transformation and integration processes. DE4LungCancer is assessed regarding the methods followed for data quality assessment and curation. Lastly, the role of controlled vocabularies and ontologies in health data management is discussed, as well as their impact on transparent knowledge extraction and analytics. This paper presents the lessons learned in the DE4LungCancer development. It demonstrates the transparency level supported by the proposed knowledge-driven ecosystem, in the context of the lung cancer pilots of the EU H2020-funded project BigMedilytic, the ERA PerMed funded project P4-LUCAT, and the EU H2020 projects CLARIFY and iASiS.
{"title":"Knowledge graphs for enhancing transparency in health data ecosystems","authors":"F. Aisopos, S. Jozashoori, E. Niazmand, Disha Purohit, Ariam Rivas, Ahmad Sakor, Enrique Iglesias, D. Vogiatzis, Ernestina Menasalvas Ruiz, A. R. González, Guillermo Vigueras, Daniel Gómez-Bravo, M. Torrente, Roberto Hernández López, M. P. Pulla, Athanasios Dalianis, A. Triantafillou, G. Paliouras, M. Vidal","doi":"10.3233/sw-223294","DOIUrl":"https://doi.org/10.3233/sw-223294","url":null,"abstract":"Tailoring personalized treatments demands the analysis of a patient’s characteristics, which may be scattered over a wide variety of sources. These features include family history, life habits, comorbidities, and potential treatment side effects. Moreover, the analysis of the services visited the most by a patient before a new diagnosis, as well as the type of requested tests, may uncover patterns that contribute to earlier disease detection and treatment effectiveness. Built on knowledge-driven ecosystems, we devise DE4LungCancer, a health data ecosystem of data sources for lung cancer. In this data ecosystem, knowledge extracted from heterogeneous sources, e.g., clinical records, scientific publications, and pharmacological data, is integrated into knowledge graphs. Ontologies describe the meaning of the combined data, and mapping rules enable the declarative definition of the transformation and integration processes. DE4LungCancer is assessed regarding the methods followed for data quality assessment and curation. Lastly, the role of controlled vocabularies and ontologies in health data management is discussed, as well as their impact on transparent knowledge extraction and analytics. This paper presents the lessons learned in the DE4LungCancer development. It demonstrates the transparency level supported by the proposed knowledge-driven ecosystem, in the context of the lung cancer pilots of the EU H2020-funded project BigMedilytic, the ERA PerMed funded project P4-LUCAT, and the EU H2020 projects CLARIFY and iASiS.","PeriodicalId":48694,"journal":{"name":"Semantic Web","volume":"41 1","pages":"943-976"},"PeriodicalIF":3.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90832625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mathias De Brouwer, Bram Steenwinckel, Ziye Fang, Marija Stojchevska, P. Bonte, Filip De Turck, Sofie Van Hoecke, F. Ongenae
Integrating Internet of Things (IoT) sensor data from heterogeneous sources with domain knowledge and context information in real-time is a challenging task in IoT healthcare data management applications that can be solved with semantics. Existing IoT platforms often have issues with preserving the privacy of patient data. Moreover, configuring and managing context-aware stream processing queries in semantic IoT platforms requires much manual, labor-intensive effort. Generic queries can deal with context changes but often lead to performance issues caused by the need for expressive real-time semantic reasoning. In addition, query window parameters are part of the manual configuration and cannot be made context-dependent. To tackle these problems, this paper presents DIVIDE, a component for a semantic IoT platform that adaptively derives and manages the queries of the platform’s stream processing components in a context-aware and scalable manner, and that enables privacy by design. By performing semantic reasoning to derive the queries when context changes are observed, their real-time evaluation does require any reasoning. The results of an evaluation on a homecare monitoring use case demonstrate how activity detection queries derived with DIVIDE can be evaluated in on average less than 3.7 seconds and can therefore successfully run on low-end IoT devices.
{"title":"Context-aware query derivation for IoT data streams with DIVIDE enabling privacy by design","authors":"Mathias De Brouwer, Bram Steenwinckel, Ziye Fang, Marija Stojchevska, P. Bonte, Filip De Turck, Sofie Van Hoecke, F. Ongenae","doi":"10.3233/sw-223281","DOIUrl":"https://doi.org/10.3233/sw-223281","url":null,"abstract":"Integrating Internet of Things (IoT) sensor data from heterogeneous sources with domain knowledge and context information in real-time is a challenging task in IoT healthcare data management applications that can be solved with semantics. Existing IoT platforms often have issues with preserving the privacy of patient data. Moreover, configuring and managing context-aware stream processing queries in semantic IoT platforms requires much manual, labor-intensive effort. Generic queries can deal with context changes but often lead to performance issues caused by the need for expressive real-time semantic reasoning. In addition, query window parameters are part of the manual configuration and cannot be made context-dependent. To tackle these problems, this paper presents DIVIDE, a component for a semantic IoT platform that adaptively derives and manages the queries of the platform’s stream processing components in a context-aware and scalable manner, and that enables privacy by design. By performing semantic reasoning to derive the queries when context changes are observed, their real-time evaluation does require any reasoning. The results of an evaluation on a homecare monitoring use case demonstrate how activity detection queries derived with DIVIDE can be evaluated in on average less than 3.7 seconds and can therefore successfully run on low-end IoT devices.","PeriodicalId":48694,"journal":{"name":"Semantic Web","volume":"27 1","pages":"893-941"},"PeriodicalIF":3.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89098743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Annotations enrich text corpora and provide necessary labels for natural language processing studies. To reason and infer underlying implicit knowledge captured by labels, an ontology is needed to provide a semantically annotated corpus with structured domain knowledge. Utilizing a corpus of adverse event documents annotated for sepsis-related signs and symptoms as a use case, this paper details how a terminology and corresponding ontology were developed. The Annotated Adverse Event NOte TErminology (AAENOTE) represents annotated documents and assists annotators in annotating text. In contrast, the complementary Catheter Infection Indications Ontology (CIIO) is intended for clinician use and captures domain knowledge needed to reason and infer implicit information from data. The approach taken makes ontology development understandable and accessible to domain experts without formal ontology training.
{"title":"Terminology and ontology development for semantic annotation: A use case on sepsis and adverse events","authors":"Melissa Y. Yan, L. Gustad, L. Høvik, Ø. Nytrø","doi":"10.3233/sw-223226","DOIUrl":"https://doi.org/10.3233/sw-223226","url":null,"abstract":"Annotations enrich text corpora and provide necessary labels for natural language processing studies. To reason and infer underlying implicit knowledge captured by labels, an ontology is needed to provide a semantically annotated corpus with structured domain knowledge. Utilizing a corpus of adverse event documents annotated for sepsis-related signs and symptoms as a use case, this paper details how a terminology and corresponding ontology were developed. The Annotated Adverse Event NOte TErminology (AAENOTE) represents annotated documents and assists annotators in annotating text. In contrast, the complementary Catheter Infection Indications Ontology (CIIO) is intended for clinician use and captures domain knowledge needed to reason and infer implicit information from data. The approach taken makes ontology development understandable and accessible to domain experts without formal ontology training.","PeriodicalId":48694,"journal":{"name":"Semantic Web","volume":"34 1","pages":"811-871"},"PeriodicalIF":3.0,"publicationDate":"2023-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74671197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Benítez-Andrades, María Teresa García-Ordás, Mayra Russo, Ahmad Sakor, Luis Daniel Fernandes Rotger, M. Vidal
Social networks have become information dissemination channels, where announcements are posted frequently; they also serve as frameworks for debates in various areas (e.g., scientific, political, and social). In particular, in the health area, social networks represent a channel to communicate and disseminate novel treatments’ success; they also allow ordinary people to express their concerns about a disease or disorder. The Artificial Intelligence (AI) community has developed analytical methods to uncover and predict patterns from posts that enable it to explain news about a particular topic, e.g., mental disorders expressed as eating disorders or depression. Albeit potentially rich while expressing an idea or concern, posts are presented as short texts, preventing, thus, AI models from accurately encoding these posts’ contextual knowledge. We propose a hybrid approach where knowledge encoded in community-maintained knowledge graphs (e.g., Wikidata) is combined with deep learning to categorize social media posts using existing classification models. The proposed approach resorts to state-of-the-art named entity recognizers and linkers (e.g., Falcon 2.0) to extract entities in short posts and link them to concepts in knowledge graphs. Then, knowledge graph embeddings (KGEs) are utilized to compute latent representations of the extracted entities, which result in vector representations of the posts that encode these entities’ contextual knowledge extracted from the knowledge graphs. These KGEs are combined with contextualized word embeddings (e.g., BERT) to generate a context-based representation of the posts that empower prediction models. We apply our proposed approach in the health domain to detect whether a publication is related to an eating disorder (e.g., anorexia or bulimia) and uncover concepts within the discourse that could help healthcare providers diagnose this type of mental disorder. We evaluate our approach on a dataset of 2,000 tweets about eating disorders. Our experimental results suggest that combining contextual knowledge encoded in word embeddings with the one built from knowledge graphs increases the reliability of the predictive models. The ambition is that the proposed method can support health domain experts in discovering patterns that may forecast a mental disorder, enhancing early detection and more precise diagnosis towards personalized medicine.
{"title":"Empowering machine learning models with contextual knowledge for enhancing the detection of eating disorders in social media posts","authors":"J. Benítez-Andrades, María Teresa García-Ordás, Mayra Russo, Ahmad Sakor, Luis Daniel Fernandes Rotger, M. Vidal","doi":"10.3233/sw-223269","DOIUrl":"https://doi.org/10.3233/sw-223269","url":null,"abstract":"Social networks have become information dissemination channels, where announcements are posted frequently; they also serve as frameworks for debates in various areas (e.g., scientific, political, and social). In particular, in the health area, social networks represent a channel to communicate and disseminate novel treatments’ success; they also allow ordinary people to express their concerns about a disease or disorder. The Artificial Intelligence (AI) community has developed analytical methods to uncover and predict patterns from posts that enable it to explain news about a particular topic, e.g., mental disorders expressed as eating disorders or depression. Albeit potentially rich while expressing an idea or concern, posts are presented as short texts, preventing, thus, AI models from accurately encoding these posts’ contextual knowledge. We propose a hybrid approach where knowledge encoded in community-maintained knowledge graphs (e.g., Wikidata) is combined with deep learning to categorize social media posts using existing classification models. The proposed approach resorts to state-of-the-art named entity recognizers and linkers (e.g., Falcon 2.0) to extract entities in short posts and link them to concepts in knowledge graphs. Then, knowledge graph embeddings (KGEs) are utilized to compute latent representations of the extracted entities, which result in vector representations of the posts that encode these entities’ contextual knowledge extracted from the knowledge graphs. These KGEs are combined with contextualized word embeddings (e.g., BERT) to generate a context-based representation of the posts that empower prediction models. We apply our proposed approach in the health domain to detect whether a publication is related to an eating disorder (e.g., anorexia or bulimia) and uncover concepts within the discourse that could help healthcare providers diagnose this type of mental disorder. We evaluate our approach on a dataset of 2,000 tweets about eating disorders. Our experimental results suggest that combining contextual knowledge encoded in word embeddings with the one built from knowledge graphs increases the reliability of the predictive models. The ambition is that the proposed method can support health domain experts in discovering patterns that may forecast a mental disorder, enhancing early detection and more precise diagnosis towards personalized medicine.","PeriodicalId":48694,"journal":{"name":"Semantic Web","volume":"42 1","pages":"873-892"},"PeriodicalIF":3.0,"publicationDate":"2023-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74201255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In both applied ontology and engineering, functionality is a well-researched topic, since it is through teleological causal reasoning that domain experts build mental models of engineering systems, giving birth to functions. These mental models are important throughout the whole lifecycle of any product, being used from the design phase up to diagnosis activities. Though a vast amount of work to model functions has already been carried out, the literature has not settled on a shared and well-defined approach due to the variety of concepts involved and the modeling tasks that functional descriptions should satisfy. The work in this paper posits the basis and makes some crucial steps towards a rich ontological description of functions and related concepts, such as behaviour, capability, and capacity. A conceptual analysis of such notions is carried out using the top-level ontology DOLCE as a framework, and the ensuing logical theory is formally described in first-order logic and OWL, showing how ontological concepts can model major aspects of engineering products in applications. In particular, it is shown how functions can be distinguished from the implementation methods to realize them, how one can differentiate between capabilities and capacities of a product, and how these are related to engineering functions.
{"title":"Towards a formal ontology of engineering functions, behaviours, and capabilities","authors":"Francesco Compagno, S. Borgo","doi":"10.3233/sw-223188","DOIUrl":"https://doi.org/10.3233/sw-223188","url":null,"abstract":"In both applied ontology and engineering, functionality is a well-researched topic, since it is through teleological causal reasoning that domain experts build mental models of engineering systems, giving birth to functions. These mental models are important throughout the whole lifecycle of any product, being used from the design phase up to diagnosis activities. Though a vast amount of work to model functions has already been carried out, the literature has not settled on a shared and well-defined approach due to the variety of concepts involved and the modeling tasks that functional descriptions should satisfy. The work in this paper posits the basis and makes some crucial steps towards a rich ontological description of functions and related concepts, such as behaviour, capability, and capacity. A conceptual analysis of such notions is carried out using the top-level ontology DOLCE as a framework, and the ensuing logical theory is formally described in first-order logic and OWL, showing how ontological concepts can model major aspects of engineering products in applications. In particular, it is shown how functions can be distinguished from the implementation methods to realize them, how one can differentiate between capabilities and capacities of a product, and how these are related to engineering functions.","PeriodicalId":48694,"journal":{"name":"Semantic Web","volume":"213 1","pages":""},"PeriodicalIF":3.0,"publicationDate":"2023-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73348103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：