The Core Domain Ontology (CDO) specifies a protocol for a canonical semantic substrate.
Browse the CDO here.
CDO defines the requirements by which meaning is anchored, interpreted, and compared across heterogeneous systems, institutions, and domains, without requiring shared vocabularies, shared ontologies, or uniform institutional models. CDO governs:
CDO applies to any system, model, ontology, or vocabulary whose semantic commitments must be made legible, comparable, or interoperable across institutional or contextual boundaries.
CDO is concerned solely with semantic interpretation and contextual anchoring. It does not govern execution, authority, evidence, enforcement, or outcomes. Those concerns are explicitly outside the scope of this protocol.
The absence of shared vocabulary, shared ontology, or direct semantic agreement SHALL NOT be interpreted as semantic failure. Divergence is expected and permitted; anchoring is required.
CDO is domain-independent and intended to function across organizational, technical, sectoral, and jurisdictional boundaries without imposing uniform models or centralized control.
]]>The objective is to develop an innovative NLP-based surveillance system to monitor substance-related harms in real-time. This AI-driven solution will gather data from various media channels, synthesizing information to provide a comprehensive overview of substance use trends, clusters of morbidity, and mortality across Canada.
The project focuses on enhancing public health response, particularly for communities disproportionately affected by substance use. Traditional surveillance methods lag in data collection; this AI-powered system offers timely insights to empower early intervention and targeted public health action.
In collaboration with the Canadian Centre on Substance Use and Addiction, Datalab at the School of Health Policy and Management at York University, and the Urban Data Research Centre at the University of Toronto, this project is funded by the Public Health Agency of Canada’s Enhanced Surveillance for Chronic Disease Program.
Key Members
In classical AI planning, replanning strategies are used to reevaluate a plan during execution. For human-like agents, goal preferences and emotions play an important role in evaluating a plan’s progress. However, most existing systems rely on predefined goal ordering and a static association between an event and its emotion-based utility calculation. During execution, utility of individual actions are used to trigger the replanning process. This approach assumes that a complete sequence of actions can be generated, preferences are known, are transitive, the mood-based utility of every action’s outcome is known, and a replanning condition is well defined. This paper presents an alternative approach, one that does not make assumptions about the agent’s or observer’s omniscience about factors influencing decision making. Our approach recognizes the bounds that limit the agent and observer equally. To accommodate these limits, first, human-centric goal ranking are grounded in a domain-specific mapping to Maslow’s hierarchy. Second, a new replanning condition is proposed with dynamically changing mood-based utility during plan execution.
The BRAMA framework is meant to emulate decisions made by a seemingly irrational human-like agent with the use of a rational reasoner. In this chapter, BRAMA extends a single decision rational reasoner using a utility function that incorporates rational and non-rational factors influencing human decision making.
For single decision making, BRAMA represents a domain as a state and a set of actions along with related terms. Future actions and outcomes are independent from past actions and outcomes. The outcome of a choice is true if the choice was made and not true if the choice was not made. Each individual action is viewed as an alternative action, and each outcome as an independent alternative outcome (Hansson2005). For example, either a person decided to go for a stroll with an umbrella, without an umbrella, or did not go for a stroll at all. Imagine they went for a stroll. If it was not raining, the outcome is a state where the person went on a stroll, has an umbrella, and enjoyed the stroll. If it was raining and they did not bring an umbrella, then the outcome is a state in which they went on a stroll, did not have an umbrella, and did not enjoy the stroll.
The nature of outcomes in single decision theory can be put more strongly: the outcomes of alternative choices are mutually exclusive of other choices available or will be available in the future. There are several ways to interpret choices and outcomes. For example, like expected utility theory (EU), prospect theory (PT) also considers choices as mutually exclusive. However, unlike EU, there is no extension to PT that provides support for a time dimension and interdependence of choices. Hence, decision theory incorporated in BRAMA is based on the EU model of utility and decision making.
]]>The Ontology of Social Service Needs (OSSN) represents service provisioning from the perspective of a cognitive, goal-driven client to evaluate services based on how well they remove a client’s constraints and meet client needs.
Browse the OSSN here.
OSSN is grounded in real-life requests made by participants of a Housing First intervention program, resulting in 58 different goal types. Each goal is mapped to one or more basic human needs defined by Maslow’s Hierarchy, as inferred from the goal’s type, the motivation behind it, and the client’s demographics. Finally, as clients interact with service providers, three different types of goal orderings are required to capture goal ranking during the planning and execution phases. These include the client’s preferred order, Maslow’s Hierarchy order, and the practical order imposed by the logistical constraints of service providers.
The Ontology of Social Service Needs (OSSN) is an ontology of needs for human-like agents that interact with a social service provisioning system. The ontology is based on data about the types of requests made by social service clients in a real-life intervention program. Existing ontologies focus on the process of service delivery, categorizing services and resources to ensure an efficient assignment of services to incoming clients. The ontology allows for the evaluation of service provisioning from the client’s perspective. By identifying goals of clients and the services that satisfy them, it is possible to create a high-fidelity client emulation model for the purpose of social service evaluation.
The ontology is developed using the ontology engineering method. Ontology engineering is a systemic way of constructing and evaluating an ontological representation of a domain. First, motivating scenarios are identified to define the scope and objectives the ontology is meant to resolve. Second, a set of informal competency questions ore defined which the ontology should answer. Third, an ontology is constructed that represents knowledge required to answer identified competency ques- tions. Finally, the informal competency questions are translated into formal competency questions using the terminology and formal language that allows for the automation of querying identified questions. The work presented here represents the ontology in OWL syntax. The SPARQL query language is used to represent formal competency questions, with a complete evaluation in
]]>The PARLANCE project is a pipeline that involves developing data translation and consolidation logic, enabling the merging of diverse data sources into a single representation stored in a knowledge graph.
PARLANCE - adaPtive grAph Repository pipeLine for dynAmic kNowledge sourCEs
The project is developed in partnership with HelpSeeker Technologies as part of the Compass project. The project was sponsored, in part, by MITACS.
]]>The research question this proposal addresses is:
Our research objectives are to:
The Common Impact Data Standard is a standardized way to represent a social purpose organization’s (SPO) impact model (i.e. their theory of change, logic model, outcome chain, etc). It is a way to represent impact as defined by the Impact Management Project Norms (now housed at Impact Frontiers). It enables the exchange of impact information between organizations regardless of the impact models being used.
We understand “impact” as a change in outcomes for people and the planet. To represent impact, the Common Impact Data Standard represents the five dimensions: what, who, how much, contribution and risk, plus a sixth dimension of how.
Built on linked data and using the JSON-LD exchange format, the Common Impact Data Standard also allows for data interoperability. This means that any aligned software can read the bespoke data sets and reports coming in from another aligned software platform. Links to data can be shared from platform to platform with little human effort.
The Common Impact Data Standard represents impact models We use “impact models” as a general term to describe a family of similar relational maps such as a logic model, logical framework analysis, a theory of change, outcome chain, impact map, results framework, and outcomes map. The Common Impact Data Standard also represents the processes by which an SPO delivers outcomes to or with its stakeholders.
The Common Impact Data Standard is defined using the OWL semantic web ontology language and conforms to linked data standards.
A widely adopted data standard will create a uniform representation of impact while allowing each organization the flexibility to design an impact model that is most relevant to it and its stakeholders.
]]>The mission of the Canadian Urban Data Catalogue (CUDC) is to provide awareness of the vast array of urban and non-urban Canadian data by providing an open catalogue of Canadian datasets. It catalogues both open and closed datasets, along with data accessible via web services. CUDC is openly available for searching and creating new catalogue entries. CUDC uses a rich metadata model that supports the documentation and search for datasets relevant to a user’s needs. Catalogue entry metadata may be exported from and imported to CUDC in bulk or entered manually.
]]>“What is a service?” The notion of “services” is inherently well understood by people, but it is difficult to define explicitly. The area of “service science” has recently been adopted to investigate the nature of services. Our project aims provide an ontological definition for the notion of a “service”. This project is inspired by out work in the social services, a community-based and locally-focused service network that relies on personal connections as much as technological advancements.
Towards this goal, we have been running workshops at JOWO on ontologies of services and the societies they shape and serve.
Past events:
Semantic Technologies provide a formal way to represent knowledge in ways that are interoperable by computers and a related technology stack to store, integrate and query information semantically.
The purpose of the OSS workshop is to foster communication and strengthen interdisciplinary work at the intersection of semantic technologies, society, and services. We invite researchers from the Knowledge Representation, Semantic Web, and Machine Learning communities to submit theoretical contributions, novel algorithms, artifacts, and tools related to the interaction of society and service provisioning. We welcome reports from sociologists and service practitioners across various society-focused domains (e.g. social workers, therapists, physicians, probation officers, urban planners, etc.) on their experiences using semantic-enabled technologies, best practices, and insights.
We welcome submissions from researchers and practitioners working at the intersection of semantic technologies and social services and social service practitioners developing ontological artifacts.