* One of the currently most important discussions in artificial intelligence is modeling personality and emotion in artificial intelligence, chiefly in Human-Computer-Interaction (HCI). The purpose of this research is designing a general model that identifies a user's affective status based on user's personality and emotion. The proposed model is composed of two main modules: personality and emotion modules. The personality module detects personality type of a user based on two approaches: determining personality through users' actions in a system and using sequential behavioral pattern mining to determine personality. In the emotion module, we propose a computational model to calculate a user's desirability based on personality in e-learning environments. The desirability of an event is one of the most important factors in determining a user's emotions. The proposed model has been evaluated in simulated and real e-learning environments. The results show that the model formulates the relationship between personality and emotions with adequate accuracy.
Nowadays, one of the most used computer applications is in Elearning. The main idea of E-learning is learning anywhere and anytime, but this type of education has brought new problems. It usually lacks dynamism and does not establish necessary interactions to attract learners’ attention.
For instance, it’s clear that during a learner’s interaction with a
computer, the learner’s emotional states changes [1] which depends
on his/her individual characteristics. Positive emotions play an
important role in creativity and flexibility for solving problems
while negative emotions block the thinking process and prevent
sound reasoning [2] [
Consequently, developers ought to concentrate designing
interactive user interfaces based on user’s affective status, and
personality aiming to make them more realistic and attractive [
Several studies have been carried out in order to consider human
characteristics in human computer interaction [
Jin Du and his colleagues [
As mentioned above, several studies have been carried out in
order to consider human characteristics in human computer
interaction especially in E-learning environments. Despite all these
efforts, to the best of our knowledge, there is no work modeling the
relationship between personality and emotion to improve the
elearning experience. Consequently, we have proposed a model to
show a relationship between personality and one of the most
important variables in determining emotions [
In addition, in this research, we used MBTI for personality modeling and the OCC model for emotion modeling. The results show the effectiveness of the proposed approaches.
In this research, we focus on designing a computational model that identifies a user’s affective status based on personality and emotion. During the user’s interaction with a computer, and depending on events happening in the environment and his personality, the user’s emotion changes. In this situation, an intelligent system should be responsive to the user’s emotions. The proposed model is composed of two main modules: the personality and emotion modules. its importance value in determining desirability. For example, based on the characteristics of an ENTJ type person, the importance value of “develop new skills” and “learn new things” are high and the impact value of “improving their level of competence” is low. The output of Goal-Personality chart to the event appraiser module is set of goals corresponding to the user’s personality. On the other hand, the output of this module to the desirability calculator is the importance value of each goal in determining the desirability based on the user’s personality.
Event appraiser: The aim of this module is to calculate the impact of environmental events on achieving the goals which are determined by the Goal-Personality chart. In other words, the output of this module determines how much the goals are achieved based on the events.
This is based on lot of evidences that show there is a relationship between personality dimensions and the events that causes individuals with different personality react in different ways. For example, asking help from a teacher in an e-learning environment is an environmental event which happened through learner.
This event is related to extroversion/introversion dimension. As we know, extroverted individuals like to ask for help from others and they like to help others. In contrast, introverted individuals prefer to perform their tasks alone without help. That is why we use the relationship between personality dimensions and events to calculate impact of environmental events on achieving the goals.
Desirability calculator: As mentioned earlier, based on the OCC model, to calculate the desirability or undesirability level of an event, it is essential to know how much an event is in line with a user’s goals. That is why the inputs to this module are the importance values of the goals, provided by the goal-personality chart, and the impact of environmental events on achieving the goals, given by the event appraiser. These inputs are used to calculate the desirability using Eq. 1.
∑ =1 = ∑ =1 ∗ ∈ [−1,1] (1) in which n is the number of goals, , given by the GoalPersonality chart, is the importance of the ith goal. Furthermore, is the achieved level of the ith goal, which is calculated based on the impact of the triggered events and the corresponding personality dimensions. Finally, represents how much the triggered events are desirable based on the user’s goals and personality. The desirability is normalized between -1 and 1 in which desirable events range between 0 and 1 while undesirable events range between 0 and -1. is calculated using Eq. 2 in which the impact of events and the personality dimensions’ levels (pdl) are considered through a linear relation between these two.
= ∑ =1 ∗
in which m is the number of events, and is the ith event.
We use an E-learning environment in order to evaluate our
proposed model. Since Furnham and Jackson clearly expressed that
the learner’s learning style is a subset of his/her personality [
MBTI learning style model in e-learning environment instead of personality.
To evaluate proposed personality module, we use a blended learning environment for the “Introduction to computing systems and programming” (ICSP) course. The course is taught to the firstyear students at the school of electrical and computer engineering (2) at the University of Tehran in Iran. The course runs for 18 weeks, and 355,155 interaction records were collected of the two hundred and twenty-six students from the Moodle’s log file. Each record includes "time", "IP address", "action", "URL", "info", "username", "first name", "last name" and "email of the corresponding student". The "time" shows the duration of time students did an activity and the "info" includes an id uniquely assigned to the page accessed/used by the students.
We define two groups of features: Learning Activity Feature (LAF) and Context-based Learning Activity Feature (CLAF). To determine the best features for predicting the learning styles, we run many important clustering methods through Weka tools. K-means (k=2) was the suitable method for separating two MBTI dimensions. K-means gives best result when data set are distinct or well separated from each other. The results show that there are nine CLAF of 112 features that separate people with different learning styles. Table 1 shows an example of the results.
The number of messages sent in the chat rooms is the best feature to separate feeling students from thinking ones. This feature confirms that feeling people tend to interact and relate to other students through discussion rooms. Table 1 shows that feeling students used chat rooms more than thinking people.
In the next step, to extract frequent behavioral sequences, we have collected the data from two hundred and fifteen students who registered in the “Introduction to computing systems and programming” (ICSP) course. We run Generalized Sequential Pattern Mining (GSP) algorithm which is an apriori-based algorithm on data. Finally, we found a lot of frequent behavioral sequences in each dimension of MBTI which some of them can be meaningful and usable to discriminate individuals. Some examples of frequent sequences are presented here: {Results of Quizzes} {Lessons} {Extra Exercises} {Add/Delete Posts} Introvert {Extra Exercise} {Quiz}{Results of Quizzes} {Lessons} Extrovert {Review}{Quiz}{Results of Quizzes} {Lessons} Thinking {Quiz}{Quiz}{Results of Quizzes} {Lessons}{Add/Delete Posts} Feeling {Review}{Quiz}{Quiz}{Results of Quizzes} {Extra Exercises} Perceiving {Lessons}{Quiz}{Add/Delete Posts} {Extra Exercises}Judging {Add/Delete Posts} {Quiz}{Quiz}{Results of Quizzes}iNtuition {Quiz}{Results of Quizzes} {Lessons}{Quizzes}Sensing
The sample of results show that there are different sequences of behaviors for different dimension of learning style. Also, we can predict the learning style of learners based on these sequences with high accuracy.
To evaluate the emotion module, we used a simulated and a real e-learning environment. In the simulated e-learning environment, 1878 artificial intelligence agents were used. The The results in table 2 and 3 show that our hypothesis about the relationship between events and achieving goals and mapping between the personality dimensions and achieving goals are correct and our expectation in desirability prediction is satisfied.
In this research, we focused on designing a user computational model that identifies the user status based on personality and emotions. To evaluate the proposed module, we used a simulated and a real e-learning environment.
In the future, we want to incorporate mood in our modeling to improve the desirability prediction by incorporating the relationship between mood, emotion, and personality. Furthermore, it is necessary to collect further data to improve the system’s accuracy. Also, modeling of other factors in emotions needs to be investigated.
This work has been partially funded by the Iranian Cognitive Sciences and Technologies Council, grant number 384.
[2] S. Chaffar and C. Frasson, "Using an Emotional Intelligent Agent to Improve the Learner’s Performance," in 7th International Conference on Intelligent Tutoring System, Brazil, 2004.