Rule based fuzzy cognitive maps and natural language processing in machine ethics

Rollin Omari, Masoud MOHAMMADIAN

    Research output: Contribution to journalArticle

    3 Citations (Scopus)

    Abstract

    Purpose: The developing academic field of machine ethics seeks to make artificial agents safer as they become more pervasive throughout society. In contrast to computer ethics, machine ethics is concerned with the behavior of machines toward human users and other machines. This study aims to use an action-based ethical theory founded on the combinational aspects of deontological and teleological theories of ethics in the construction of an artificial moral agent (AMA). Design/methodology/approach: The decision results derived by the AMA are acquired via fuzzy logic interpretation of the relative values of the steady-state simulations of the corresponding rule-based fuzzy cognitive map (RBFCM). Findings: Through the use of RBFCMs, the following paper illustrates the possibility of incorporating ethical components into machines, where latent semantic analysis (LSA) and RBFCMs can be used to model dynamic and complex situations, and to provide abilities in acquiring causal knowledge. Research limitations/implications: This approach is especially appropriate for data-poor and uncertain situations common in ethics. Nonetheless, to ensure that a machine with an ethical component can function autonomously in the world, research in artificial intelligence will need to further investigate the representation and determination of ethical principles, the incorporation of these ethical principles into a system’s decision procedure, ethical decision-making with incomplete and uncertain knowledge, the explanation for decisions made using ethical principles and the evaluation of systems that act based upon ethical principles. Practical implications: To date, the conducted research has contributed to a theoretical foundation for machine ethics through exploration of the rationale and the feasibility of adding an ethical dimension to machines. Further, the constructed AMA illustrates the possibility of utilizing an action-based ethical theory that provides guidance in ethical decision-making according to the precepts of its respective duties. The use of LSA illustrates their powerful capabilities in understanding text and their potential application as information retrieval systems in AMAs. The use of cognitive maps provides an approach and a decision procedure for resolving conflicts between different duties. Originality/value: This paper suggests that cognitive maps could be used in AMAs as tools for meta-analysis, where comparisons regarding multiple ethical principles and duties can be examined and considered. With cognitive mapping, complex and abstract variables that cannot easily be measured but are important to decision-making can be modeled. This approach is especially appropriate for data-poor and uncertain situations common in ethics.
    Original languageEnglish
    Pages (from-to)231-253
    Number of pages23
    JournalJournal of Information, Communication and Ethics in Society
    Volume14
    Issue number3
    DOIs
    Publication statusPublished - 2016

    Fingerprint

    Decision making
    moral philosophy
    Processing
    language
    Semantics
    Information retrieval systems
    Machine components
    Fuzzy logic
    Artificial intelligence
    Dynamic models
    decision making
    semantics
    Cognitive Map
    Fuzzy
    Natural Language Processing
    artificial intelligence
    logic
    information retrieval
    Ethical Principles
    simulation

    Cite this

    @article{b9d56a861dfb4122951577c995410223,
    title = "Rule based fuzzy cognitive maps and natural language processing in machine ethics",
    abstract = "Purpose: The developing academic field of machine ethics seeks to make artificial agents safer as they become more pervasive throughout society. In contrast to computer ethics, machine ethics is concerned with the behavior of machines toward human users and other machines. This study aims to use an action-based ethical theory founded on the combinational aspects of deontological and teleological theories of ethics in the construction of an artificial moral agent (AMA). Design/methodology/approach: The decision results derived by the AMA are acquired via fuzzy logic interpretation of the relative values of the steady-state simulations of the corresponding rule-based fuzzy cognitive map (RBFCM). Findings: Through the use of RBFCMs, the following paper illustrates the possibility of incorporating ethical components into machines, where latent semantic analysis (LSA) and RBFCMs can be used to model dynamic and complex situations, and to provide abilities in acquiring causal knowledge. Research limitations/implications: This approach is especially appropriate for data-poor and uncertain situations common in ethics. Nonetheless, to ensure that a machine with an ethical component can function autonomously in the world, research in artificial intelligence will need to further investigate the representation and determination of ethical principles, the incorporation of these ethical principles into a system’s decision procedure, ethical decision-making with incomplete and uncertain knowledge, the explanation for decisions made using ethical principles and the evaluation of systems that act based upon ethical principles. Practical implications: To date, the conducted research has contributed to a theoretical foundation for machine ethics through exploration of the rationale and the feasibility of adding an ethical dimension to machines. Further, the constructed AMA illustrates the possibility of utilizing an action-based ethical theory that provides guidance in ethical decision-making according to the precepts of its respective duties. The use of LSA illustrates their powerful capabilities in understanding text and their potential application as information retrieval systems in AMAs. The use of cognitive maps provides an approach and a decision procedure for resolving conflicts between different duties. Originality/value: This paper suggests that cognitive maps could be used in AMAs as tools for meta-analysis, where comparisons regarding multiple ethical principles and duties can be examined and considered. With cognitive mapping, complex and abstract variables that cannot easily be measured but are important to decision-making can be modeled. This approach is especially appropriate for data-poor and uncertain situations common in ethics.",
    keywords = "Decision making and ethics, Natural language processing in machine ethics, Rule based fuzzy cognitive maps",
    author = "Rollin Omari and Masoud MOHAMMADIAN",
    year = "2016",
    doi = "10.1108/JICES-10-2015-0034",
    language = "English",
    volume = "14",
    pages = "231--253",
    journal = "Journal of Information, Communication and Ethics in Society",
    issn = "1477-996X",
    publisher = "Emerald Group Publishing Ltd.",
    number = "3",

    }

    Rule based fuzzy cognitive maps and natural language processing in machine ethics. / Omari, Rollin; MOHAMMADIAN, Masoud.

    In: Journal of Information, Communication and Ethics in Society, Vol. 14, No. 3, 2016, p. 231-253.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Rule based fuzzy cognitive maps and natural language processing in machine ethics

    AU - Omari, Rollin

    AU - MOHAMMADIAN, Masoud

    PY - 2016

    Y1 - 2016

    N2 - Purpose: The developing academic field of machine ethics seeks to make artificial agents safer as they become more pervasive throughout society. In contrast to computer ethics, machine ethics is concerned with the behavior of machines toward human users and other machines. This study aims to use an action-based ethical theory founded on the combinational aspects of deontological and teleological theories of ethics in the construction of an artificial moral agent (AMA). Design/methodology/approach: The decision results derived by the AMA are acquired via fuzzy logic interpretation of the relative values of the steady-state simulations of the corresponding rule-based fuzzy cognitive map (RBFCM). Findings: Through the use of RBFCMs, the following paper illustrates the possibility of incorporating ethical components into machines, where latent semantic analysis (LSA) and RBFCMs can be used to model dynamic and complex situations, and to provide abilities in acquiring causal knowledge. Research limitations/implications: This approach is especially appropriate for data-poor and uncertain situations common in ethics. Nonetheless, to ensure that a machine with an ethical component can function autonomously in the world, research in artificial intelligence will need to further investigate the representation and determination of ethical principles, the incorporation of these ethical principles into a system’s decision procedure, ethical decision-making with incomplete and uncertain knowledge, the explanation for decisions made using ethical principles and the evaluation of systems that act based upon ethical principles. Practical implications: To date, the conducted research has contributed to a theoretical foundation for machine ethics through exploration of the rationale and the feasibility of adding an ethical dimension to machines. Further, the constructed AMA illustrates the possibility of utilizing an action-based ethical theory that provides guidance in ethical decision-making according to the precepts of its respective duties. The use of LSA illustrates their powerful capabilities in understanding text and their potential application as information retrieval systems in AMAs. The use of cognitive maps provides an approach and a decision procedure for resolving conflicts between different duties. Originality/value: This paper suggests that cognitive maps could be used in AMAs as tools for meta-analysis, where comparisons regarding multiple ethical principles and duties can be examined and considered. With cognitive mapping, complex and abstract variables that cannot easily be measured but are important to decision-making can be modeled. This approach is especially appropriate for data-poor and uncertain situations common in ethics.

    AB - Purpose: The developing academic field of machine ethics seeks to make artificial agents safer as they become more pervasive throughout society. In contrast to computer ethics, machine ethics is concerned with the behavior of machines toward human users and other machines. This study aims to use an action-based ethical theory founded on the combinational aspects of deontological and teleological theories of ethics in the construction of an artificial moral agent (AMA). Design/methodology/approach: The decision results derived by the AMA are acquired via fuzzy logic interpretation of the relative values of the steady-state simulations of the corresponding rule-based fuzzy cognitive map (RBFCM). Findings: Through the use of RBFCMs, the following paper illustrates the possibility of incorporating ethical components into machines, where latent semantic analysis (LSA) and RBFCMs can be used to model dynamic and complex situations, and to provide abilities in acquiring causal knowledge. Research limitations/implications: This approach is especially appropriate for data-poor and uncertain situations common in ethics. Nonetheless, to ensure that a machine with an ethical component can function autonomously in the world, research in artificial intelligence will need to further investigate the representation and determination of ethical principles, the incorporation of these ethical principles into a system’s decision procedure, ethical decision-making with incomplete and uncertain knowledge, the explanation for decisions made using ethical principles and the evaluation of systems that act based upon ethical principles. Practical implications: To date, the conducted research has contributed to a theoretical foundation for machine ethics through exploration of the rationale and the feasibility of adding an ethical dimension to machines. Further, the constructed AMA illustrates the possibility of utilizing an action-based ethical theory that provides guidance in ethical decision-making according to the precepts of its respective duties. The use of LSA illustrates their powerful capabilities in understanding text and their potential application as information retrieval systems in AMAs. The use of cognitive maps provides an approach and a decision procedure for resolving conflicts between different duties. Originality/value: This paper suggests that cognitive maps could be used in AMAs as tools for meta-analysis, where comparisons regarding multiple ethical principles and duties can be examined and considered. With cognitive mapping, complex and abstract variables that cannot easily be measured but are important to decision-making can be modeled. This approach is especially appropriate for data-poor and uncertain situations common in ethics.

    KW - Decision making and ethics

    KW - Natural language processing in machine ethics

    KW - Rule based fuzzy cognitive maps

    UR - http://www.scopus.com/inward/record.url?scp=84982986550&partnerID=8YFLogxK

    UR - http://www.mendeley.com/research/rule-based-fuzzy-cognitive-maps-natural-language-processing-machine-ethics

    U2 - 10.1108/JICES-10-2015-0034

    DO - 10.1108/JICES-10-2015-0034

    M3 - Article

    VL - 14

    SP - 231

    EP - 253

    JO - Journal of Information, Communication and Ethics in Society

    JF - Journal of Information, Communication and Ethics in Society

    SN - 1477-996X

    IS - 3

    ER -