Automated classification of complex social survey questionnaires is crucial for large-scale social science research but faces significant reliability challenges due to intricate hierarchical label structures, severe class imbalance, semantic ambiguity, and incomplete data coverage. Conventional classification methods often struggle with these combined complexities, yielding results that lack trustworthiness. We introduce HOCM, a framework designed for trustworthy classification in complex, real-world taxonomies. It features two synergistic components: (1) memory-enhanced contrastive learning, tailored to learn robust representations from noisy, imbalanced data by leveraging quality-aware category memory banks; and (2) hierarchical uncertainty calibration, which enforces taxonomic consistency while providing reliable confidence estimates and identifying inputs falling outside well-represented known categories. Our evaluation on a large-scale, real-world social survey dataset—a challenging exemplar of our target problem class—demonstrates that HOCM maintains strong accuracy on known classes while effectively identifying uncertain cases, significantly boosting accuracy on confident predictions. Furthermore, it adeptly detects low-resource/unknown categories. HOCM provides a more reliable automated classification tool, enabling efficient expert review and enhancing the trustworthiness of analysis in domains with complex, hierarchical data.

Predicting vehicle traffic optimizes transportation management and urban planning. In this article, we combine real-time data from vehicle-detection Internet of Things (IoT) devices with external variables from Google Trends. Integrating such heterogeneous, complex data streams is challenging for traditional machine learning models that struggle to capture the dynamics of traffic patterns, which are influenced by multiple interdependent factors. To effectively model these complex, interdependent factors, we introduce the Granger-Causal Transformer (GCT), a transformer-based architecture for traffic prediction that integrates an LSTM network with a modified multi-head attention mechanism. This mechanism extends Granger causality to the spatio-temporal domain to analyze all causality relations between features consistently, while capturing long-range dependencies and temporal patterns. Before applying GCT, we generate lagged versions of the Google Trends time series to capture lead and lag effects. Tourists usually make searches about their destination weeks before traveling, so peaks in search interest occur earlier than peaks in weekly traffic volume. Using lags aligns the predictors with weekly traffic volume and allows the model to use past searches to predict future traffic. We semantically validate the Google Trends terms by comparing each term with a reference string describing the study area, using a language model aligned with the data’s linguistic context. We then apply a dual filtering process comprising Granger noncausality and correlation tests to minimize noise and redundancy. We evaluate our proposed methodology against classical statistical models, deep learning models, large foundation models, and transformers across two case studies. The results demonstrate consistently superior performance and generalizability, with GCT achieving \(R^{2}\) improvements between 47% and 68% compared to the best-performing baselines across both settings, alongside substantial reductions in MAE and MSE.

Vocabularies such as the European Language Social Science Thesaurus (ELSST) and the CLOSER ontology are the foundational taxonomies capturing core social science concepts that form the foundations of large-scale longitudinal social science surveys. However, standard text embeddings often fail to capture the complex hierarchical and relational structures of the sociological concepts, relying on surface similarity. In this work, we propose a framework to model these nuances by adapting a large language model based text embedding model with a learnable diagonal Riemannian metric. This metric allows for a flexible geometry where dimensions can be scaled to reflect semantic importance. Additionally, we introduce a Hierarchical Ranking Loss with dynamic margins as the sole training objective to enforce the multi-level hierarchical constraints (e.g., distinguishing 'self' from narrower, broader, or related concepts, and all from 'unrelated' ones) from ELSST within the Riemannian space, such as ensuring a specific concept like 'social stratification' is correctly positioned by, for instance, being embedded closer to 'social inequality' (as its broader, related concept) and substantially further from an 'unrelated' concept like 'particle physics'. Lastly, we show that our parameter-efficient approach significantly outperforms strong contrastive learning and hyperbolic embedding baselines on hierarchical concept retrieval and classification tasks using the ELSST and CLOSER datasets. Visualizations confirm the learned embedding space exhibits a clear hierarchical structure. Our work offers a more accurate and geometrically informed method for representing complex sociological constructs.

Understanding online conversations has attracted research attention with the growth of social networks and online discussion forums. Content analysis of posts and replies in online conversations is difficult because each individual utterance is usually short and may implicitly refer to other posts within the same conversation. Thus, understanding individual posts requires capturing the conversational context and dependencies between different parts of a conversation tree and then encoding the context dependencies between posts and comments/replies into the language model. To this end, we propose a general-purpose mechanism to discover appropriate conversational context for various aspects about an online post in a conversation, such as whether it is informative, insightful, interesting or funny. Specifically, we design two families of Conversation Kernels, which explore different parts of the neighborhood of a post in the tree representing the conversation and through this, build relevant conversational context that is appropriate for each task being considered. We apply our developed method to conversations crawled from slashdot.org, which allows users to apply highly different labels to posts, such as `insightful', `funny', etc., and therefore provides an ideal experimental platform to study whether a framework such as Conversation Kernels is general-purpose and flexible enough to be adapted to disparately different conversation understanding tasks. We perform extensive experiments and find that context-augmented conversation kernels can significantly outperform transformer-based baselines, with absolute improvements in accuracy up to 20% and up to 19% for macro-F1 score. Our evaluations also show that conversation kernels outperform state-of-the-art large language models including GPT-4. We also showcase the generalizability and demonstrate that conversation kernels can be a general-purpose approach that flexibly handles distinctly different conversation understanding tasks in a unified manner.

Automated detection of semantically equivalent questions in longitudinal social science surveys is crucial for long-term studies informing empirical research in the social, economic, and health sciences. Retrieving equivalent questions faces dual challenges: inconsistent representation of theoretical constructs (i.e. concept/sub-concept) across studies as well as between question and response options, and the evolution of vocabulary and structure in longitudinal text. To address these challenges, our multi-disciplinary collaboration of computer scientists and survey specialists presents a new information retrieval (IR) task of identifying concept (e.g. Housing, Job, etc.) equivalence across question and response options to harmonise longitudinal population studies. This paper investigates multiple unsupervised approaches on a survey dataset spanning 1946-2020, including probabilistic models, linear probing of language models, and pre-trained neural networks specialised for IR. We show that IR-specialised neural models achieve the highest overall performance with other approaches performing comparably. Additionally, the re-ranking of the probabilistic model's results with neural models only introduces modest improvements of 0.07 at most in F1-score. Qualitative post-hoc evaluation by survey specialists shows that models generally have a low sensitivity to questions with high lexical overlap, particularly in cases where sub-concepts are mismatched. Altogether, our analysis serves to further research on harmonising longitudinal studies in social science.

As Internet of Things (IoT) technologies become more widespread in everyday life , privacy issues are becoming more prominent. The aim of this research is to develop a personal assistant that can answer software engineers’ questions about Privacy by Design (PbD) practices during the design phase of IoT system development. Semantic web technologies are used to model the knowledge underlying PbD measurements, their intersections with privacy patterns, IoT system requirements and the privacy patterns that should be applied across IoT systems. This is achieved through the development of the PARROT ontology, developed through a set of representative IoT use cases relevant for software developers. This was supported by gathering Competency Questions (CQs) through a series of workshops, resulting in 81 curated CQs. These CQs were then recorded as SPARQL queries, and the developed ontology was evaluated using the Common Pitfalls model with the help of the Protégé HermiT Reasoner and the Ontology Pitfall Scanner (OOPS!), as well as evaluation by external experts. The ontology was assessed within a user study that identified that the PARROT ontology can answer up to 58% of privacy-related questions from software engineers.

Unsupervised topic modelling is a useful unbiased mechanism for topic labelling of complex longitudinal questionnaires covering multiple domains such as social science and medicine. Manual tagging of such complex datasets increases the propensity of incorrect or inconsistent labels and is a barrier to scaling the processing of longitudinal questionnaires for provision of question banks for data collection agencies. Towards this effort, we propose a tailored BERTopic framework that takes advantage of its novel sentence embedding for creating interpretable topics, and extend it with an enhanced visualisation for comparing the topic model labels with the tags manually assigned to the question literals. The resulting topic clusters uncover instances of mislabelled question tags, while also enabling showcasing the semantic shifts and evolution of the topics across the time span of the longitudinal questionnaires. The tailored BERTopic framework outperforms existing topic modelling baselines for the quantitative evaluation metrics of topic coherence and diversity, while also being 18 times faster than the next best-performing baseline.

Our aim is to create a personal assistant, a chatbot, that can answer queries from software developers regarding Privacy by Design (PbD) methods and applications throughout the design phase of IoT system development. We used semantic web technologies to model the PARROT Ontology that includes knowledge underlying PbD measurements, their intersections with privacy patterns, IoT system needs, and the privacy patterns that should be applied across IoT systems. To determine the PARROT ontology's requirements, a collection of real-world IoT use cases were aided by a series of workshops to gather Competency Questions (CQs) from researchers and software engineers, resulting in 81 selected CQs. In a user study, the PARROT ontology was able to answer up to 58% of software developers' privacy-related issues. The technical report \citeorca149337 contains further analysis and results from data collecting and intermediate synthesis steps.

Text classification techniques have been substantially important to many smart computing applications, e.g. topic extraction and event detection. However, classification is always challenging when only insufficient amount of labelled data for model training is available. To mitigate this issue, zero-shot learning (ZSL) has been introduced for models to recognise new classes that have not been observed during the training stage. We propose an entailment-based zero-shot text classification model, named as S-BERT-CAM, to better capture the relationship between the premise and hypothesis in the BERT embedding space. Two widely used textual datasets are utilised to conduct the experiments. We fine-tune our model using 50% of the labels for each dataset and evaluate it on the label space containing all labels (including both seen and unseen labels). The experimental results demonstrate that our model is more robust to the generalised ZSL and significantly improves the overall performance against baselines.

Internet of Things (IoT) refers to an ecosystem where applications and services are driven by data collected from devices interacting with each other and the physical world. Although IoT has already brought spectacular benefits to human society, the progress is actually not as fast as expected. From network structures to control flow graphs, IoT naturally generates an unprecedented volume of graph data continuously, which stimulates fertilization and making use of advanced graph-powered methods on the diverse, dynamic, and large-scale graph IoT data.

Advances in communication technologies and artificial intelligence are accelerating the paradigm of industrial Internet of Things (IIoT). With IIoT enabling continuous integration of sensors and controllers with the network, intelligent analysis of the generated Big Data is a critical requirement. Although IIoT is considered a subset of IoT, it has its own peculiarities in terms of higher levels of safety, security, and low-latency communication in an environment of critical real-time operations. Under these circumstances, discriminative deep learning (DL) algorithms are unsuitable due to their need for large amounts of labeled and balanced training data, uncertainty of inputs, etc. To overcome these issues, researchers have started using deep generative models (DGMs), which combine the flexibility of DL with the inference power of probabilistic modeling. In this article, we review the state of the art of DGMs and their applicability to IIoT, classifying the reviewed works into the IIoT application areas of anomaly detection, trust-boundary protection, network traffic prediction, and platform monitoring. Following an analysis of existing IIoT DGM implementations, we identify challenges (i.e., weak discriminative capability, insufficient interpretability, lack of generalization ability, generated data vulnerability, privacy concern, and data complexity) that need to be investigated in order to accelerate the adoption of DGMs in IIoT and also propose some potential research directions.

The Internet of Things (IoT) aims to connect everyday physical objects to the internet. These objects will produce a significant amount of data. The traditional cloud computing architecture aims to process data in the cloud. As a result, a significant amount of data needs to be communicated to the cloud. This creates a number of challenges, such as high communication latency between the devices and the cloud, increased energy consumption of devices during frequent data upload to the cloud, high bandwidth consumption, while making the network busy by sending the data continuously, and less privacy because of less control on the transmitted data to the server. Fog computing has been proposed to counter these weaknesses. Fog computing aims to process data at the edge and substantially eliminate the necessity of sending data to the cloud. However, combining the Service Oriented Architecture (SOA) with the fog computing architecture is still an open challenge. In this paper, we propose to decompose services to createlinked-microservices(LMS).Linked-microservicesare services that run on multiple nodes but closely linked to their linked-partners.Linked-microservicesallow distributing the computation across different computing nodes in the IoT architecture. Using four different types of architectures namely cloud, fog, hybrid, and fog+cloud, we explore and demonstrate the effectiveness of service decomposition by applying four experiments to three different type of datasets. Evaluation of the four architectures shows that decomposing services into nodes reduce the data consumption over the network by 10 - 70 percent. Overall, these results indicate that the importance of decomposing services in the context of fog computing for enhancing the quality of service.

Social media platforms such as Twitter are increasingly used to collect data of all kinds. During natural disasters, users may post text and image data on social media platforms to report information about infrastructure damage, injured people, cautions and warnings. Effective processing and analysing tweets in real time can help city organisations gain situational awareness of the affected citizens and take timely operations. With the advances in deep learning techniques, recent studies have significantly improved the performance in classifying crisis-related tweets. However, deep learning models are vulnerable to adversarial examples, which may be imperceptible to the human, but can lead to model's misclassification. To process multi-modal data as well as improve the robustness of deep learning models, we propose a multi-modal adversarial training method for crisis-related tweets classification in this paper. The evaluation results clearly demonstrate the advantages of the proposed model in improving the robustness of tweet classification.

With technologies developed in the Internet of Things, embedded devices can be built into every fabric of urban environments and connected to each other; and data continuously produced by these devices can be processed, integrated at different levels, and made available in standard formats through open services. The data, obviously f a form of `big data', is now seen as the most valuable asset in developing intelligent applications. As the sizes of the IoT data continue to grow, it becomes inefficient to transfer all the raw data to a centralised, cloud-based data centre and to perform efficient analytics even with the state-of-the-art big data processing technologies. To address the problem, this article demonstrates the idea of "distributed intelligence" for sensor data computing, which disperses intelligent computation to the much smaller while autonomous units, e.g., sensor network gateways, smart phones or edge clouds in order to reduce data sizes and to provide high quality data for data centres. As these autonomous units are usually in close proximity to data consumers, they also provide potential for reduced latency and improved quality of services. We present our research on designing methods and apparatus for distributed computing on sensor data, e.g., acquisition, discovery, and estimation, and provide a case study on urban air pollution monitoring and visualisation.

In pervasive environments, availability and reliability of a service cannot always be guaranteed. In such environments, automatic and dynamic mechanisms are required to compose services or compensate for a service that becomes unavailable during the runtime. Most of the existing works on services composition do not provide sufficient support for automatic service provisioning in pervasive environments. We propose a Divide and Conquer algorithm that can be used at the service runtime to repeatedly divide a service composition request into several simpler sub-requests. The algorithm repeats until for each sub-request we find at least one atomic service that meets the requirements of that sub-request. The identified atomic services can then be used to create a composite service. We discuss the technical details of our approach and show evaluation results based on a set of composite service requests. The results show that our proposed method performs effectively in decomposing a composite service requests to a number of sub-requests and finding and matching service components that can fulfill the service composition request.

As the number of Linked Data sets increases with more and more interconnections defined between them, querying a single data set is no longer enough for users who need data from mixed domains. The requirement to query data from different data sets motivates the research into federated queries. Network latency is one of the key factors which affect the performance of a federated query. The influence of network latency can be minimised by decreasing the number of remote requests, which is related to the number of joins. In this paper, we provide a mechanism for federated querying based on subject and sameAs grouping techniques. Exploiting the benefits of proposed grouping methods, the number of joins during a federated query has been reduced, thus improving the performance of the entire query. We have evaluated our approach against other existing approaches, using an existing benchmark suite and found that our approach performs better than comparable approaches for queries that are not highly selective.

Semantic modeling for the Internet of Things has become fundamental to resolve the problem of interoperability given the distributed and heterogeneous nature of the "Things". Most of the current research has primarily focused on devices and resources modeling while paid less attention on access and utilisation of the information generated by the things. The idea that things are able to expose standard service interfaces coincides with the service oriented computing and more importantly, represents a scalable means for business services and applications that need context awareness and intelligence to access and consume the physical world information. We present the design of a comprehensive description ontology for knowledge representation in the domain of Internet of Things and discuss how it can be used to support tasks such as service discovery, testing and dynamic composition.

This paper proposes an extension to Session Initiation Protocol (SIP) for contextualized service delivery in a service delivery platform (SDP) that enables device specific multimedia delivery. SIP separates between session establishment and description and is thus, amenable to be extended for advanced implementations which make it an ideal platform for service creation. Device specific multimedia delivery needs rich and flexible device descriptions, and our approach proposes advanced device descriptions through semantic technologies. The proposed SIP extensions have been implemented on a SIP Application Server which functions as SDP in IP Multimedia Subsystem (IMS). The validation of the proposed extensions is shown through an Android SIP client application that acts as a device browser and recommender for different multimedia services to users. An example device user agent (UA) application has also been implemented on a laptop.

Multimedia services are becoming increasingly popular among mobile users. Ontology and related technologies have been introduced into the multimedia domain as a means to provide declarative formal representations of the domain knowledge and thus to enable intelligent multimedia processing, such as media format adaptation. The range of devices available to access media content becomes increasingly heterogeneous and at the same time ubiquitous. Users expect to access their services and content without restrictions in time or location. Users have many and different gadgets/devices with network connectivity at their disposal to receive content, ranging from their smart phones, car audio systems to laptops, or office PCs, etc. Hence there is a need to link the discovery and the description of these ambient device with multimedia domain knowledge representations in order to facilitate a ubiquitous multimedia experience. The contribution of this work is an approach for mapping device descriptions, which are leveraged on the resource discovery protocol UPnP to OWL ontology instances. The ontology instances chosen are compliant with the MPEG-21 DIA OWL-formatted ontology. This approach bridges the gap between non-semantic description mechanisms of the legacy device/services discovery protocol with the semantic multimedia domain knowledge representation.

The vision of service personalization for mobile communication environments entails context sensitive service provisioning. The realization of such customizable smart spaces necessitates acquisition and processing of modality context information from a variety of devices in the ambient environment. The heterogeneity of available device capabilities and description formats brings new challenges for a context reasoning engine that formulates content delivery decisions. Specifically, to ensure interoperability with existing application logic, the enabling components should support semantic queries. Secondly, situations where variously formatted context input may not provide enough information to answer queries, should be intelligently handled. Towards this aim, this paper discusses a context reasoning and query interface component as part of a service context manager (SCM) framework that supports semantic querying and handles incomplete context information through a rule-based mechanism. The validation of the approach is provided by showing the mapping of disparate UAProf and UPnP descriptions into the framework and querying of supported modality services.