Establish long-term social relationships between human and artificial agent that

Author Topic: Establish long-term social relationships between human and artificial agent that  (Read 45 times)

Offline ismail-324

  • Newbie
  • *
  • Posts: 1
  • Allah Help Me
    • View Profile
    • News & Multimedia
Research Plan

Research Topic: Establish long-term social relationships between human and artificial agent that gives advice to
a human

1 Introduction
We know that social relationships play an important role in human life. We interact daily with computers that appear
and behave like humans. Some researchers propose that people apply the same social norms to computers as they do
to humans, suggesting that social psychological knowledge can be applied to our interactions with computers. When
an intelligent agent gives some advice to a human, it depends on trust in artificial agents. Here, social relationship
plays an important role. When human to human advice each and others, it also depends on trust. At first, we justify
adviser qualification then we took advice from that human. In this study, we have focused on trust in artificial agents
and we need to establish social relationships in human and artificial agents. Trust on artificial agents is a thriving
research area in which lots of advancements like automatic communication systems, machine to human interaction,
human to machine interaction are happening in industries. In these studies, we build long term social relationships
in human and artificial agents. We also recognize trust in agents.

2 Problem Identification
Trust to artificial agents is a complex and extensive research topic, Human trust to agents plays an important role
in the interaction between human and machine communication. If human or artificial agent doesn’t trust each and
others, we failed to communicate human to artificial agents, artificial agents to human. Nowadays, the analysis of
human trust for artificial agents is essential for social communication. In the modern world, we used machine for
every single work and its make our life so easier. At the same time when we depend on artificial agents, there’s
create a lot of gaps to trust in artificial agents. In our research, we try to build trust in artificial agents when that
agent gives some advice to human and establish long term social relationships between human and artificial agents.

3 Methodology
3.1 Social Relationship between Human and Agent
We can more easily attribute personality to computers than to other machines. Personalized agents, therefore,
are naturally regarded as human-like interactants, and consequently, people tend to expect these agents to behave
intellectually in the same way as humans. However, disappointment is felt when the agents behave contrary to human
expectations and this leads some people to believe that the agents are not useful at all. Accordingly, the design of
an agent must be carefully considered to keep people from excessive anticipation. In general, computers are simply
considered machines to support practical jobs. Therefore, people implicitly and naturally expect any computer to
settle their affairs as an inherent function. Interface agents, however, have changed the social relationship between
humans and computers to an operator-collaborator relationship. In this study, we examine how to build long term
social relationships that maintain equal relationships between human and artificial agents.

3.2 Trust Solutions for Human{Agent Interaction
The first section of the theme issue is dedicated to trust solutions for human and artificial agents. If agents are to be
introduced to human environments, they need to be endowed with interaction capabilities. This requires an enormous
effort in the fields of engineering and artificial intelligence and covers areas such as face and emotion recognition,
action and intention prediction, speech processing and many others. Indeed, social robots need to be able to sense
signals from humans, respond adequately, understand and generate natural language, have reasoning capacities, plan
actions and execute movements in line with what is required by the specific context or situation. In, a simple set
of protocols is proposed to allow learning interface agents to collaborate in order to learn from each other. It was
important for such agents to determine which fellow agents to trust since the users they were derived from possibly
had very dissimilar behavior. The main protocols were: the exploratory protocol, where the agent asks the other
1agent questions for which it already knows the answer. The agent then increases the trust rating of the agents who
give the expected answer. the query protocol, where the agent asks for advice from trusted agents.

3.3 Establishing and Maintaining social Relationships
The appearance of a person has a great effect on first impressions. The appearance-based interpersonal attraction
of an agent will also have such an effect on the user’s first impression of the agent. This will induce the user’s
affiliation need in the first encounter. Therefore, the appearance of the interface agent is important in establishing
the social relationship between the user and the agent. When human find that the agent help them a lot, they
want to maintain a long term relationship with an agents. In the other hands when they find out an agent make
some negative attitude, they don’t continue a relationship with the agent. Human orientation of establishing and
maintaining social relationships can be adapted to interactions with interface agents.

3.4 Security Approach
At this level, basic structural properties are guaranteed, like the authenticity and integrity of messages, privacy,
agents’ identities, etc. When an artificial agent gives some advice to a human, then it needs to be security for communication. In this study, we create custom security plans that protect our data when artificial agents communicate
with humans.

4 My contribution to the proposed research
The contribution this research aimed to make can be divided into two-part...
1. Feature extraction
2. Final prediction
On the feature extraction phase, We will build a custom data set which will contain agent data suggestion for human.
Data collection is a little difficult for this data set.
In the final prediction phase, We will collect the data from online but there is not available such kind of data online
that’s why we collect data also questioning methods. After collecting data we input the data to artificial agent and
the agent give advice to human.

5 References
[1]Cross ES, Hortensius R, Wykowska A. 2019 From social brains to social robots: applying neurocognitive insights
to human { robot interaction. Phil. Trans. R. Soc. B 374: 20180024.
[2] Takeuchi, Y. and Y. Katagiri, "Social Character Design for Animated Agents," in RO-MAN99. 1999.
[3] Babak Esfandiari1, Sanjay Chandrasekharan2."On How Agents Make Friends: Mechanisms for Trust Acquisition"
Department of Systems and Computer Engineering,Carleton University, Ottawa, Ontario, Canada,,
2 Cognitive Science Ph.D. Program, Carleton University, Ottawa, Ontario, Canada,
[4] Katagiri, Y, Takahashi, T, Takeuchi, Y. "Social Persuasion in Human-Agent Interaction"
[5] Pinyol, I, Sabater-Mir, J.(2011) "Computational trust and reputation models for open multi-agent systems: a
review" DOI 10.1007/s10462-011-9277-z