The Rise in Artificial Intelligence Makes Emotional Intelligence More Important
OVERVIEW
Emotions and Intelligence are a co-related phenomenon; therefore emotions must be taken into consideration for designing truly intelligent agent. Emotional intelligence has emerged as an important area of research in artificial intelligence covering wide range of real-life domains. A significant contribution are being made to bring new insights in the field of emotional intelligence and the development of intelligent software agents. Learning agents and educational activities are attractive areas for the incorporation of emotional aspects of artificial intelligence. Emotions have an important role in intelligent behavior and influence the human decision-making process. In this article, we will focus on emotional intelligence research with an emphasis on areas such as Emotion detection, Emotional agents, Text emotion detection, Modeling artificial agent’s environments.
- INTRODUCTION
The concept of Emotional Intelligence became prominent in the late 1980’s; however, Thorndike discussed a similar concept called social intelligence much earlier, in 1920 [1]. While one’s social intelligence is typically defined by an “ability to understand and manage other people, and to engage in adaptive social interactions” [2]; emotional intelligence deals specifically with one’s ability to perceive, understand, manage, and express emotion within oneself and in dealing with others [3]. Salovey et.al, define five domains critical to emotional intelligence: knowing one’s emotions, managing emotions, motivating one, recognizing emotions in others, and handling relationships. A common measure of Emotional Intelligence is EQ (emotional intelligence quotient), as gauged by a myriad of widely published EQ tests.
Figure 1: Domains of Emotional IntelligenceMany researchers in artificial intelligence and human computer interaction started to take emotions seriously in the late 1990s. Picard gave a framework for building machines with emotional intelligence. Subsequently, many other researchers in this area have built machines that can reason with emotions, and also detect, handle, understand and express emotions. Efforts in building emotionally intelligent entities continue to be concentrated in the following areas:
- Empowering the machine to detect emotions
- Enabling the machine to express emotion
- Embodying the machine in a virtual or physical way
An Intelligent Agent (IA) [4] – [11] is considered to be a software entity located in an environment. IA can be
- Autonomous;
- respond to changes in the environment;
- be proactive in attaining its goals; and also
- Sociable.
For the purpose of attaining the goal, an IA learns by itself and makes use of its internal knowledge base. Thus, it is seen as natural metaphor for human acts. It has an elevated performance behavior in data distribution and control of self-imposed expertise.
There are five categories in the Intelligent Agent based systems: -
- Integration: Integration of information and sharing of knowledge.
- Coordination: Cooperative problem-solving and multi-agent systems.
- Mobility: Mobile agent/ object solutions.
- Assistance: Personal assistance, soft-bots and data mining.
- Believable Agents: Alife and simulation.
- EMOTION DETECTION
Artificial emotional intelligence or Emotion AI is also known as emotion recognition or emotion detection technology. In market research, this is commonly referred to as facial coding. Work in the space of automated approaches to detecting emotion has focused on many different inputs including verbal cues, non-verbal cues including gestures and facial expressions, bodily signals such as skin conductivity as well as textual information. The end goal in building systems that are able to detect an emotional response from a user, is to handle/understand that response and act accordingly – a problem that is larger and less understood than the problem of simply detecting the emotional responses/expression in the first place.
Sentiment Analysis is already widely used by different companies to gauge consumer mood towards their product or brand in the digital world. However, in the offline world users are also interacting with the brands and products in retail stores, showrooms, etc. and solutions to measure user’s reaction automatically under such settings have remained a challenging task. Emotion Detection from facial expressions using AI can be a viable alternative to automatically measure consumer’s engagement with their content and brands.
- EMOTIONAL AGENTS
An emotional agent is an agent that interacts with its environment based on balanced evaluations of the impact that the states of that environment have on the goals, beliefs and overall concerns of that agent.
Figure 2: Overall structure of an emotional agent- Different Aspects of considering Emotional Agents:
- Emotional Perception
- Emotional Reasoning
- Emotional Memory
- Emotional Learning
- Emotional Expression
Emotions will have an impact on the following: Perception, Beliefs, Reasoning and Decision Making, and finally Action and Expression.
Figure 3: Emotional Agents as Hybrid Structure
- Different Aspects of considering Emotional Agents:
- TEXT EMOTION DETECTION
Emotions are an important aspect in the interaction and communication between individuals. The exchange of emotions through text messages and posts of personal blogs poses an informal kind of writing challenge for researches. Extraction of emotions from text will applied for deciding the human computer interaction that governs communication. Emotions are also expressed by a person’s speech pattern, facial expressions, and words used. Emotions are also expressed by one word or a string of words. Sentence level emotion detection technique plays a vital role in tracing emotions or to look out for the cues for generating such emotions. Sentences are the essential info units of any document. For that reason, the document level feeling detection technique depends on the feeling expressed by the individual sentences of that document that in turn depends on the emotions expressed by the individual words.
Emotion detection in computational linguistics is the process of identifying discrete emotion expressed in text. Emotion analysis can be viewed as a natural evolution of sentiment analysis and its more fine-grained model.
The rapid growth of the World Wide Web has facilitated increased on-line communication, blog posts and written content over websites and opens the new avenues to detect the emotions from that text data. This has led to generation of large amounts of online content rich in user opinions, emotions, and sentiments [4]. A computational approach is required to successfully analyze this online content, detect emotions, and draw useful conclusions. Existing techniques tend to deal with polarity recognition of sentiment. The sentiment may be positive or negative.
- Emotion detection approaches
Emotion detection approaches use or modify concepts and general algorithms created for subjectivity and sentimental analysis. There are many approaches that are being used and explored. However, many of the approaches have few similarities in them. Some of the methods available are presented here.
- Keyword-based Methods
Keywords based approaches use synonyms and antonyms are WordNet to determine word sentiments based on a set of seed opinion words. A bootstrapping approach is proposed, which uses a small set of given seed opinion words to find their synonyms and antonyms in WordNet to predict the semantic orientation of adjective. In WordNet the adjectives are in bipolar cluster form of organization and have synonyms have same orientation. As all the adjectives are linked and it form a pattern and leads to the emotion which the word depict.
- Vector Space Model
Categorical classification is used in the approach of Vector Space Model(VSM). Matrix of cooccurrence frequency vectors are used to represent the dataset dimensionally. Words are represented by rows and the columns that can represent sentences, paragraphs or documents. Therefore, the column and the row depict a relationship. VSM weighs these frequencies using the tf-idf weighting schema. The tf-idf score is the weight of each word in terms of its importance within the dataset of documents.
- Keyword-based Methods
- Emotion detection approaches
- MODELING ARTIFICIAL AGENT’S ENVIRONMENTS
AI is about practical reasoning: reasoning in order to do something. A coupling of perception, reasoning, and acting comprise an agent. An agent acts in an environment. An agent's environment may well include other agents. An agent together with its environment is called a worl
Figure 4: An agent interacting with an environmentPresently, AI is increasingly dependent on cloud computing. The goals should be to model the range of hunger human emotions, as well as their dynamics. There are different frameworks, libraries, applications, toolkits, and datasets in the AI and machine learning would. By creating a direct neural interface with the internet, humankind will be able to “plug into” higher intelligence. The five components of AI with emotional intelligence are as follows: deep learning, self-awareness, safety and ethics, external awareness and big data collection and processing moderns (shown in Fig. 5). Emotions are essential part of human intelligence and without emotional intelligence, AI is incomplete.
Figure 5: Artificial Intelligence with Emotional Intelligence Models - CONCLUSION
The creation of machines that are empowered with emotional intelligence is a research area that is growing within the field of artificial intelligence. It has long been known that AI and automation/robotics will change markets and workforces. Self-driving cars will force over three thousand truck drivers to seek new forms of employment, and robotic production lines like Tesla’s will continue to eat away at manufacturing jobs, which are currently at 12 million and falling. But this is just the beginning of the disruption. As AI improves, which is happening quickly, a much broader set of “thinking” rather than “doing” jobs will be affected.
REFERENCES
- Thorndike, E.L. 1920. Intelligence and its use. Harper's Magazine, 140, 227-235.
- Kihlstrom, J., and Cantor, N. Social Intelligence. in R.J. Sternberg (Ed.), Handbook of intelligence, 2nd ed. (pp. 359-379). Cambridge, U.K.: Cambridge University Press, 2000.
- Salovey, P. Mayer, J.D. 1990. Emotional intelligence. Imagination, Cognition, and Personality, 9, 185-211.
- Balakrishnan. S and K L Shunmuganathan. Article: A JADE Implementation of Integrated Agent System for E-Mail Coordination (IASEC). International Journal of Computer Applications 58(5): 5-9, November 2012.
- S.Balakrishnan, “An Overview of Agent Based Intelligent Systems and Its Tools”, CSI Communications magazine, Volume No. 42, Issue No. 10, January 2019, pp. 15-17.
- S.Balakrishnan, “Agent based Bioinformatics Integration using JADE – Overview”, CSI Communications magazine, Volume No. 43, Issue No. 9, December 2019, pp. 29-31.
- Balakrishnan S and Steven Uatuaromuinjo Tjiraso, “Integration of Agent Based Computing with Cloud Computing: Towards Cloud Intelligent Systems”, International Research Publication House, Delhi. Engineering and Technology: Recent Innovations & Research, ISBN- 978-93-86138-06-4, pp. 1-17.
- S. Balakrishnan, K.N. Sivabalan and J. Janet “MASFE - Mutliagent System for Filtering E-Mails Using JADE”, Advanced Engineering Research and Applications (AERA), Research India Publications, ISBN- 978-93-84443-42-9, pp. 148-167, 2017.
- P.Arivazhagan, Balakrishnan. S and K L Shunmuganathan. “An Agent Based Centralized Router with Dynamic Connection Management Scheme Using JADE”, International Journal of Applied Engineering Research, ISSN 0973-4562, Volume 11, Number 3 (2016) pp 2036-2041.
- Balakrishnan. S and K L Shunmuganathan, R. Sreenevasan, “Amelioration of Artificial Intelligence using Game Techniques for an Imperfect Information Board Game Geister” International Journal of Applied Engineering Research (IJAER). ISSN 0973-4562. Vol 9, Number 22 (2014) pp. 11849-11860.
- Balakrishnan. S and K L Shunmuganathan, An Agent Based Collaborative Spam Filtering Assistance Using JADE”, International Journal of Applied Engineering Research, ISSN 0973-4562, Volume 10, Number 21 (2015) pp 42476-42479.
- A.Jebaraj Rathnakumar, S.Balakrishnan, Design Of Multi-Agent Based Systems For Entrusted Communication Using JADE”, Taga Journal of Graphic Technology, Vol. 14, pp. 766-774, 2018.
Author Write up
Dr.S.Balakrishnan is a Professor and Head, Department of Computer Science and Business Systems at Sri Krishna College of Engineering and Technology, Coimbatore, Tamilnadu, India. He has 17 years of experience in teaching, research and administration. He has published over 15 books, 3 Book Chapters, 21 Technical articles in CSI Communications Magazine, 1 article in Electronics for You (EFY) magazine, 3 articles in Open Source for You Magazine and over 100 publications in highly cited Journals and Conferences. Some of his professional awards include: Faculty with Maximum Publishing in CSI Communications 2017-2019, International Data Science Writer of the Year 2019, MTC Global Outstanding Researcher Award, Contributors Competition Winner July 2019, August 2019 and September 2019 by DataScience Foundation, with cash prize of £100, 100 Inspiring Authors of India, Deloitte Innovation Award - Cash Prize Rs.10,000/- from Deloittee for Smart India Hackathon 2018, Patent Published Award, Impactful Author of the Year 2017-18. His research interests are Artificial Intelligence, Cloud Computing and IoT. He has delivered several guest lectures, seminars and chaired a session for various Conferences. He is serving as a Reviewer and Editorial Board Member of many reputed Journals and acted as Session chair and Technical Program Committee member of National conferences and International Conferences at Vietnam, China, America and Bangkok. He has published more than 19 Patents on IoT Applications.