Ants in the OCEAN: Modulating Agents with Personality for Planning with Humans

Ahrndt, Sebastian; Aria, Armin; Fähndrich, Johannes; Albayrak, Şahin

doi:10.1007/978-3-319-17130-2_1

Cited by 10 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research on the personalities of automated agents includes the work of Mennicken et al [29] on the perceived personality traits of smart homes. Moreover, Ahrndt, Aria, Fähndrich and Albayrak [30] discussed how automated agents could be bestowed with personality traits to improve predictability in interactions with humans during planning tasks. Culley and Madhavan [31], however, raised the concern that anthropomorphic agents may strengthen human trust due to increased emotional appeal but decrease user sensitivity to actual performance because users would make trust-based judgements.…”

Section: Methodsmentioning

confidence: 99%

Putting a Face on Algorithms: Personas for Modeling Artificial Intelligence

Karahasanovic

Følstad

Schittekat

2021

Artificial Intelligence in HCI

View full text Add to dashboard Cite

We propose a new type of personas, artificial intelligence (AI) personas, as a tool for designing systems consisting of both human and AI agents. Personas are commonly used in design practices for modelling users. We argue that the personification of AI agents can help multidisciplinary teams in understanding and designing systems that include AI agents. We propose a process for creating AI personas and the properties they should include, and report on our first experience using them. The case we selected for our exploration of AI personas was the design of a highly automated decision support tool for air traffic control. Our first results indicate that AI personas helped designers to empathise with algorithms and enabled better communication within a team of designers and AI and domain experts. We call for a research agenda on AI personas and discussions on potential benefits and pitfalls of this approach.

show abstract

Section: Methodsmentioning

confidence: 99%

Putting a Face on Algorithms: Personas for Modeling Artificial Intelligence

Karahasanovic

Følstad

Schittekat

2021

Artificial Intelligence in HCI

View full text Add to dashboard Cite

show abstract

“…Taking this observation into account, one can argue that the FFM theory is a conceptual framework about human personality traits that can, for example, be used to integrate other theories about human personalities into its structure [10,16]. The reason for using the FFM of personality instead of other popular personality theories can be found elsewhere [1].…”

Section: Five-factor Modelmentioning

confidence: 97%

Predictability in human-agent cooperation

Ahrndt¹,

Breitung²,

Fähndrich³

et al. 2015

Proceedings of the 30th Annual ACM Symposium on Applied Computing

Self Cite

View full text Add to dashboard Cite

Making artificial agents a constituent part of human activities leads to more affiliated teamwork scenarios and at the same time introduces several new challenges. One challenge is the team members' ability to be mutually predictable, which is required to effectively plan own actions, e.g., in the field of human-aware planning. This work approaches the question whether or not agents are able to learn the personality of a human during interaction. In particular, we developed an agent model able to learn human personality during repeatedly played rounds in the Colored Trails Game. Human personality is described using a psychological theory of personality types known as the Five-Factor Model. The results indicate that some characteristics of a personality can be learned more accurately/easily than others.

show abstract

“…These approaches have yielded important insights regarding how building evacuations should be conducted for example [607], and, in particular, in the management of 'bottlenecks' in crowds, to avoiding potentially catastrophic panic movements [208]. Another example of application is in human-robot teamwork scenarios: an agent can use a model of human behaviour to predict the next actions of the people its interacting with, and plan its own next action accordingly [608].…”

Section: Resultsmentioning

confidence: 99%

“…Different models have been developed to represent personality differences in human, such as Eysenck's 3-factor model [614], the Myers-Briggs Type Indicator (MBTI) [627] or the Five-factor model (also known as the OCEAN model, for Openness, Conscientiousness, Extraversion, Agreeableness, Neuroticism, which are said five factors) [608], [628]. They can mediate patterns of interaction and collective behaviour.…”

Section: Resultsmentioning

confidence: 99%

“…[654]- [656]; correspondences have been found between the two frameworks [657], [658], showing them to be both accurate assessments of personality. Ahrndt et al [608] provide a comparison between the features of both models, and conclude that the FFM is better suited for models of crowds. Subjects' personalities along the FFM are often evaluated through the use of the Revised Neuroticism, Extraversion, Openness Personality Inventory (NEO-PI-R) [659]- [665], a 240 questions long questionnaire.…”

Section: Study Subjects and Foraging Taskmentioning

confidence: 99%

See 1 more Smart Citation

Collective Behaviour: From Cells to Humans

Duteil¹

View full text Add to dashboard Cite

Living in organised groups is a strategy that can be observed in a multitude of diverse species. Among such species, the behaviour of an individual on their own is not the same as within a group: the environment is modified by the presence of more subjects, individuals interact with each other, and from those interactions complex patterns of behaviour can emerge. Some species of animals almost exclusively exist as groups, and as a consequence, studying them in a social context is the only way to understand their behaviour in nature. This is the idea that drives all the research presented in this thesis: the particular behaviour exhibited by the group is so robust that it will emerge even in a very simplified environment. By observing the individual and the group in those simplified experimental conditions, it is possible to deduce rules that might govern the interaction. The importance of interactions in the group's behaviour can then be demonstrated by implementing a computer model of agents following those rules and comparing it with natural and experimental behaviour. This thesis presents different examples of such analyses, and gives illustrations of the range of questions that can be answered through this method. Groups of stem cells, juvenile sea bass and human beings were successively observed and tracked in suitable environments, with or without perturbation. The data extracted from those experiments were then processed so as to correct recording errors, and individual and collective behaviours were derived from those data, returning new insights on the nature of the interaction at the individual level, their consequences at the global level, as well as the effects of the interaction on both. Finally, I present the computer models derived from those analyses.Many systems in nature share this property of global behaviours emerging from deterministic local interaction, and as a consequence studies of this kind could shed light on important questions, of which cancer treatment, ocean acidification and human organisations are but a few examples.

show abstract

Ants in the OCEAN: Modulating Agents with Personality for Planning with Humans

Cited by 10 publications

References 25 publications

Putting a Face on Algorithms: Personas for Modeling Artificial Intelligence

Putting a Face on Algorithms: Personas for Modeling Artificial Intelligence

Predictability in human-agent cooperation

Collective Behaviour: From Cells to Humans

Contact Info

Product

Resources

About