scholarly journals Intrinsic motivation in virtual assistant interaction for fostering spontaneous interactions

PLoS ONE ◽  
2021 ◽  
Vol 16 (4) ◽  
pp. e0250326
Author(s):  
Chang Li ◽  
Hideyoshi Yanagisawa
Keyword(s):  
Artificial Intelligence ◽  
Intrinsic Motivation ◽  
Free Choice ◽  
High Expectation ◽  
Hypothetical Model ◽  
User Interactions ◽  
Two Factors ◽  
Choice Period ◽  
Motivation Model ◽  
User Motivation

With the growing utility of today’s conversational virtual assistants, the importance of user motivation in human–artificial intelligence interactions is becoming more obvious. However, previous studies in this and related fields, such as human–computer interaction, scarcely discussed intrinsic motivation (the motivation to interact with the assistants for fun). Previous studies either treated motivation as an inseparable concept or focused on non-intrinsic motivation (the motivation to interact with the assistant for utilitarian purposes). The current study aims to cover intrinsic motivation by taking an affective engineering approach. A novel motivation model is proposed, in which intrinsic motivation is affected by two factors that derive from user interactions with virtual assistants: expectation of capability and uncertainty. Experiments in which these two factors are manipulated by making participants believe they are interacting with the smart speaker “Amazon Echo” are conducted. Intrinsic motivation is measured both by using questionnaires and by covertly monitoring a five-minute free-choice period in the experimenter’s absence, during which the participants could decide for themselves whether to interact with the virtual assistants. Results of the first experiment showed that high expectation engenders more intrinsically motivated interaction compared with low expectation. However, the results did not support our hypothesis that expectation and uncertainty have an interaction effect on intrinsic motivation. We then revised our hypothetical model of action selection accordingly and conducted a verification experiment of the effects of uncertainty. Results of the verification experiment showed that reducing uncertainty encourages more interactions and causes the motivation behind these interactions to shift from non-intrinsic to intrinsic.

Effect of Expectancies on Intrinsic Motivation

1981 ◽  
Vol 49 (2) ◽  
pp. 423-428 ◽  
Author(s):  
J. Curtis Russell ◽  
O. Lee Studstill ◽  
Rebecca M. Grant
Keyword(s):  
Intrinsic Motivation ◽  
Free Choice ◽  
Performance Task ◽  
Internal Feedback ◽  
Group Feedback ◽  
The Third ◽  
External Feedback ◽  
Choice Period

The present study investigated the hypothesis that expectancies for rewards inherent in a task (working a Soma puzzle) increase intrinsic motivation for the task. Stronger expectancies of task-inherent rewards were predicted when performance was maximally informative about correct responses. Informativeness of performance was varied by giving one group of subjects feedback directly from performance (task-internal feedback), another group feedback from a source outside the task (task-external feedback), and a third group feedback from both sources (mixed feedback). Intrinsic motivation was measured by the time spent working the puzzle during a 10-min. free-choice period. Questionnaire items measured (1) informativeness of performance and (2) expectancies that the performance would be rewarding. As predicted, task-internal feedback made performance more informative and resulted both in stronger expectancies of task-inherent rewards and greater intrinsic motivation for the puzzle than task-external feedback. The third group showed intermediate values on all measures.

scholarly journals Expert System for Diagnosis of Uterine Myomas using the Certainty Factor Method

2021 ◽  
Vol 1 (4) ◽  
pp. 103-108
Author(s):  
Syahrizal Dwi Putra ◽  
M Bahrul Ulum ◽  
Diah Aryani
Keyword(s):  
Artificial Intelligence ◽  
Decision Making ◽  
Expert System ◽  
Computer System ◽  
Decision Making Process ◽  
Certainty Factor ◽  
Uterine Myomas ◽  
Factor Method ◽  
Two Factors

An expert system which is part of artificial intelligence is a computer system that is able to imitate the reasoning of an expert with certain expertise. An expert system in the form of software can replace the role of an expert (human) in the decision-making process based on the symptoms given to a certain level of certainty. This study raises the problem that many women experience, namely not understanding that they have uterine myomas. Many women do not understand and are not aware that there are already symptoms that are felt and these symptoms are symptoms of the presence of uterine myomas in their bodies. Therefore, it is necessary for women to be able to diagnose independently so that they can take treatment as quickly as possible. In this study, the expert will first provide the expert CF values. Then the user / respondent gives an assessment of his condition with the CF User values. In the end, the values obtained from these two factors will be processed using the certainty factor formula. Users must provide answers to all questions given by the system in accordance with their current conditions. After all the conditions asked are answered, the system will display the results to identify that the user is suffering from uterine myoma disease or not. The Expert System with the certainty factor method was tested with a patient who entered the symptoms experienced and got the percentage of confidence in uterine myomas/fibroids of 98.70%. These results indicate that an expert system with the certainty factor method can be used to assist in diagnosing uterine myomas as early as possible.

scholarly journals AIoT Application for Food Recommendation based on Emotion Analysis

2021 ◽  
pp. 44-53
Author(s):  
Shivangi Ruhela ◽  
Pragati Chaudhary ◽  
Rishija Shrivas ◽  
Deepti Chopra
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Decision Making ◽  
Data Exchange ◽  
The Internet ◽  
Human Intervention ◽  
User Interactions ◽  
Emotion Analysis ◽  
Efficiency Performance ◽  
Analyze Data

Artificial Intelligence(AI) and Internet of Things(IoT) are popular domains in Computer Science. AIoT converges AI and IoT, thereby applying AI into IoT. When ‘things’ are programmed and connected to the Internet, IoT comes into place. But when these IoT systems, can analyze data and have decision-making potential without human intervention, AIoT is achieved. AI powers IoT through Decision-Making and Machine Learning, IoT powers AI through data exchange and connectivity. With the AI’s brain and IoT’s body, the systems can have shot-up efficiency, performance and learning from user interactions. Some studies show that, by 2022, AIoT devices such as drones to save rainforests or fully automated cars, would be ruling the computer industries. The paper discusses AIoT at a greater depth, focuses on few case studies of AIoT for better understanding on practical levels, and lastly, proposes an idea for a model which suggests food through emotion analysis.

Intrinsic Motivation Model Based on Reward Gating

2021 ◽  
pp. 688-699
Author(s):  
Matej Pecháč ◽  
Igor Farkaš
Keyword(s):  
Intrinsic Motivation ◽  
Model Based ◽  
Motivation Model

scholarly journals Quality-time-complexity universal intelligence measurement

2018 ◽  
Vol 2 (1) ◽  
pp. 18-26
Author(s):  
Wen Ji ◽  
Jing Liu ◽  
Zhiwen Pan ◽  
Jingce Xu ◽  
Bing Liang ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Intelligent Agents ◽  
Time Complexity ◽  
Measurement Method ◽  
Machine Intelligence ◽  
Machine Learning Techniques ◽  
Content Type ◽  
Two Factors ◽  
Major Factors ◽  
Artificial Intelligence Systems

Purpose With development of machine learning techniques, the artificial intelligence systems such as crowd networks are becoming more and more autonomous and smart. Therefore, there is a growing demand to develop a universal intelligence measurement so that the intelligence of artificial intelligence systems can be evaluated. This paper aims to propose a more formalized and accurate machine intelligence measurement method. Design/methodology/approach This paper proposes a quality–time–complexity universal intelligence measurement method to measure the intelligence of agents. Findings By observing the interaction process between the agent and the environment, we abstract three major factors for intelligence measure as quality, time and complexity of environment. Practical implications In a crowd network, a number of intelligent agents are able to collaborate with each other to finish a certain kind of sophisticated tasks. The proposed approach can be used to allocate the tasks to the agents within a crowd network in an optimized manner. Originality/value This paper proposes a calculable universal intelligent measure method through considering more than two factors and the correlations between factors which are involved in an intelligent measurement.

scholarly journals Automatic Judgement of Online Video Watching: I Know Whether or Not You Watched

Mathematics ◽  
2020 ◽  
Vol 8 (10) ◽  
pp. 1827
Author(s):  
Eunseon Yi ◽  
Heuiseok Lim ◽  
Jaechoon Jo
Keyword(s):  
Free Choice ◽  
Model Verification ◽  
Time Interval ◽  
Online Video ◽  
Video Viewing ◽  
Two Factors ◽  
Experimental Subjects

Videos have long been viewed through the free choice of customers, but in some cases currently, watching them is absolutely required, for example, in institutions, companies, and education, even if the viewers prefer otherwise. In such cases, the video provider wants to determine whether the viewer has honestly been watching, but the current video viewing judging system has many loopholes; thus, it is hard to distinguish between honest viewers and false viewers. Time interval different answer popup quiz (TIDAPQ) was developed to judge honest watching. In this study, TIDAPQ randomly inserts specially developed popup quizzes in the video. Viewers must solve time interval pass (RESULT 1) and individually different correct answers (RESULT 2) while they watch. Then, using these two factors, TIDAPQ immediately performs a comprehensive judgement on whether the viewer honestly watched the video. To measure the performance of TIDAPQ, 100 experimental subjects were recruited to participate in the model verification experiment. The judgement performance on normal watching was 93.31%, and the judgement performance on unusual watching was 85.71%. We hope this study will be useful in many areas where watching judgements are needed.

scholarly journals Autonomous development and learning in artificial intelligence and robotics: Scaling up deep learning to human-like learning

2017 ◽  
Vol 40 ◽  
Author(s):  
Pierre-Yves Oudeyer
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Social Learning ◽  
Intrinsic Motivation ◽  
Scaling Up ◽  
Learning Systems ◽  
Natural Interaction ◽  
Autonomous Choice ◽  
Autonomous Development ◽  
And Robotics

AbstractAutonomous lifelong development and learning are fundamental capabilities of humans, differentiating them from current deep learning systems. However, other branches of artificial intelligence have designed crucial ingredients towards autonomous learning: curiosity and intrinsic motivation, social learning and natural interaction with peers, and embodiment. These mechanisms guide exploration and autonomous choice of goals, and integrating them with deep learning opens stimulating perspectives.

Effects of Asynchronous Music on Students’ Lesson Satisfaction and Motivation at the Situational Level

2014 ◽  
Vol 33 (3) ◽  
pp. 326-341 ◽  
Author(s):  
Nikolaos Digelidis ◽  
Costas Karageorghis ◽  
Anastasia Papapavlou ◽  
Athanasios G. Papaioannou
Keyword(s):  
Intrinsic Motivation ◽  
Mixed Model ◽  
Music Teacher ◽  
Background Music ◽  
Experimental Conditions ◽  
Positive Effects ◽  
Main Effect ◽  
Two Factors ◽  
And Gender ◽  
Senior Students

The aim of this study was to examine the effects of asynchronous (background) music on senior students’ motivation and lesson satisfaction at the situational level. A counterbalanced mixed-model design was employed with two factors comprising condition (three levels) and gender (two levels). Two hundred students (82 boys, 118 girls; Mage = 16.3 years) volunteered to participate in the study. A lesson was developed and delivered under three experimental conditions: a) teacher-selected music condition; b) student-selected music condition; and c) a no-music control condition. Mixed-model 3 (Condition) × 2 (Gender) ANOVAs were applied to examine the effects of experimental manipulations. No Condition × Gender interaction was observed, although there was a main effect for Condition. When the lesson was delivered under the two music conditions, students scored significantly higher in lesson satisfaction, intrinsic motivation, identified regulation and reported lower scores for external regulation and amotivation. The present results support the notion that the use of background music has potentially positive effects on students’ lesson satisfaction and intrinsic motivation, although neither gender nor who selected the music (teacher vs. students) had any moderating influence on the results.

Sign in / Sign up

Export Citation Format

Share Document