Discriminating Real From Fake Smiles With Galvanic Skin Response: A Critical Review

Purpose of Report

Technology has become one of most effective and responsive friend of human. There are various significant areas and approaches that are helping the humans in doing research on their daily responses and activities. Psychology and neuroscience has played great role in establishing advancement in this domain of operations (Abbas, 2016). In contrast with these facts, the contemporary research going on based upon the facial expressions of human to detect their accuracy with respect to state of mind related to human and these aspects are entirely based on the critical situations on factual basis (Iwasaki & Noguchi, 2016). Galvanic Skin Response is one of the most effective and innovative responses collected from the human that states the accuracy of smile with respect to state of mind.  This field has greater chances of innovation and improvisations, as well as these can be used for developing other areas of science in order to mandate the development perspective of technology for the sake of human comfort.

1.2 Purpose of Report 

This report is aiming at analyzing the importance and significance of understanding the accuracy of facial expressions (Specifically smile) in order to use these for other research areas that provides benefits to human as well as growth of technology. In contrast with these facts, this report has considered one research article “Observer’s Galvanic Skin Response for Discriminating Real from Fake Smiles” (Hossain, Gedeon &  Sankaranarayana, 2017). Henceforth, this report is conducting one critical review on this particular article in order to highlight the usages and advancements identified within this specific area of technological development. This report is also considering three related articles for being reviewed within this report in order assess their relevance with the concerned research article about Discrimination of Real from Fake Smiles (Knapton, Bäck & Bäck, 2015). In contrast with these facts, gap analysis of the concerned literature is also performed within this report in order to identify the future scope involved within this research article.

1.3 Key Items and Scope of Report

The key items involved within this report are the concerned approaches and facts that are concerned during the research process in order to understand the advances involved within discriminating fake and real smiles with Galvanic Skin Responses (Bartlett et al., 2014). There is various technological advancement that needs the support of Galvanic Skin responses in order to detect real and fake smiles. These functional areas and research segments are recognized as the scope of this research process in order to mandate the goals and objective behind this research. In contrast with these facts, some of the scopes are being elaborated as follows:

• To innovate new technological advancements by Galvanic Skin responses
• To understand the importance and effectiveness of emotion detection among human
• To innovate new advancements in psychological domain in order to study human behavior deeply
• To observe variable changes among human emotions

Key Items and Scope of Report

2. Critical Review

2.1 Summary of Research Article

This article is elaborating about a system that discriminates real from fake smiles with high accuracy by sensing observer’s Galvanic Skin Response (GSR) (Hossain, Gedeon &  Sankaranarayana, 2017). It is critically evaluated that these galvanic skin responses generally demonstrates signals recorded for some set of observers who took part in the experiment in testing the responses of observers. In addition to this, this is identified that this observing process is monitored for recording the responses of human with respect to various computed features and functionalities (Knowles, 2014). This article is concerned about the classification of emotions with respect to three different classifiers involved within systematic observation process.

One neural network is using random subset features for which the outer performances of the users are measured with respect to various signal responses identified within the systematic responses (Hossain, Gedeon &  Sankaranarayana, 2017). The critical responses gathered from highlights and potential responses of human are gathered with respect to various other perspectives involved within the observation process of emotional and behavioral changes being incorporated within human.  

The GSR signals are considered as the main element involved within this article as this signal shows the impactful areas of human behaviors and the changes involved within the stimuli collected from GSR signals are passed through various significant stages in order to collect the perfect and proper responses from that significant signal (Kunstman et al., 2016). The following figure is showing the impactful areas where the GSR signal is processes in order to get the noise free signals at the end (Hossain, Gedeon &  Sankaranarayana, 2017). This critical analyzed that the aim of this research article is to identify a classifier and one feature selection method that can predict the hidden mental state of mind of the observers.

According to Hossain, Gedeon and Sankaranarayana (2016), there are mainly two features of the considered system for emotional change detection. These features are nothing but the process of recording the responses and the extracted version of features. The recorded features involved within this research is concerned with each point of time that is generally changed according to situations and treated as one of the most important features of this kind of observation (Hossain, Gedeon &  Sankaranarayana, 2017). In contrast with these facts, the extracted features are based on the GSR features that are considered as temporal features within the tests performed on the normalized signal involved within tests done on observers.

General Overview and List of Specific Points on Article

2.2 General Overview and List of Specific Points on Article

2.2.1 General Overview

The general overview on any article is concerned with the response recording system that is designed based on the introduction of GSR signals within the response recording system for managing identifying the responses coming from different observers in order to collect various responses from discriminatory tests performed on human’s emotional state of mind (Hossain, Gedeon &  Sankaranarayana, 2017). This behavioral study on the emotional state of mind is tested with respect to various situations involved within tests. The GSR signals are transferred through various stages in order to test the emotional state of mind that is raised because of changes in visuals. Galvanic Skin Response is one of the most effective and innovative responses collected from the human that states the accuracy of smile with respect to state of mind.  

These responses are utilized for identifying human state of mind and their behavioral disorders with respect to different variable situations in their life. This article is generally elaborating about the processes of reducing noises from GSR signals in order to take pure emotional state of mind. This is identified from the critical review of the article that there are various emotional fluctuations incorporated within human mind that generates noises which deduces the accuracy of generated responses. Henceforth, these noises should be reduced with respect to emotional state of mind in order to manage the systematic response collection of emotional state of mind. The modification processes of GSR signals are one of the core and impactful areas identified within this research article that helps in reducing these noises involved within the GSR signals (Hossain, Gedeon &  Sankaranarayana, 2017).

2.2.2 List of Specific Points on Article

Modification of GSR signals: The modifications of GSR signals are done with the help of one significant model. This model states that the emotional state of human is identified with the help of the signals coming through the GSR signals to the researchers (Hossain, Gedeon &  Sankaranarayana, 2017). These signals contain various types of noise elements within it that makes them imperfect with respect to situation. Therefore, the model of modifying these signals helps the researchers in understanding the correct pattern of the signals with respect to situations and needs of the researchers. In addition to this, the responses collected through these GSR signals helps the researchers in understanding the patterns and mental conditions of human.

Strengths of Article

Aim of Experiment: The core aim of this experiment is to present the study that helps in finding one classifier as well as to identify one feature selection method to be appropriately used within the observer’s GSR features (Hossain, Gedeon &  Sankaranarayana, 2017). In addition to this, these GSR features are helpful in predicting the hidden mental state of mind that states the behavior of the person with respect to various critical and analytical situations generally human face.

Features: In contrast with various conditional aspects and mentioned facts within the concerned article, it is clear that the there are total features that are identified to be highlighted within the elaboration of this article. These two features are recorded features and extracted features. Recorded features are nothing but the process of recording the functionalities that are identified during the test of emotional state of persons (Hossain, Gedeon &  Sankaranarayana, 2017). In addition to this, there are total 9000 features that are identified during the experiment and among all of these features the responsive features are recorded in case of the experiment. In addition to this, in case of the extracted features, these are nothing but the process of extraction of recorded signals in order to identify the features of the emotional state of the mind among the participants.

2.3 Strengths of Article

This article is elaborating about the identification of patterns that are highlighted in case of classifying the fake and real smile patterns among a group of participants within this test. Therefore, some positive aspects and strengths are being identified within this article with respect to various facts and competitive advantages over change of emotional state among human. These strengths are being elaborated within this part of the report. These strengths are given as follows:

Identification of flawless emotional states: This is one of the most effective strength of this article as this can show the accurate state of mind and flawless emotional states to the researcher for analyzing the state of mind (Hossain, Gedeon &  Sankaranarayana, 2017). The GSR signals would be the main advancement used in mobile application as the KNN, SBBS and other included features will be less recommended for that aspect. Therefore, this can be states that the emotional states can be critically evaluated with respect to the guidelines provided by this standard.

Utilization of emotional states for identification of mental health: The mental health of human can be easily checked with the help of systematic observation of the emotional states among human. The changes of behaviors and impactful areas of human psychology can be easily checked and monitored through this experiment.

Discrimination of complex and simple mental growth: Discrimination of complex and simple mental health growth can easily be studied with the help of this technologically sound experiment (Hossain, Gedeon &  Sankaranarayana, 2017). Therefore, this experiment is one useful element for studying complex human behavior with respect to various critical situations.  

Analysis of observer’s condition: Different observer have different point of view for optimizing their understanding about some facts or responses. Therefore, this experiment is one of the most significant elements that helps the observers in studying their thinking patterns about some impactful scenarios or incidents.

3. Literature Review

4. Literature Gap 

Literature gap is nothing but the untouched areas of research that were not considered by the researcher while considering the developmental perspective of the research work. A gap is termed as something that remains to be done or learned within the areas of research. It is nothing but a gap in knowledge of researchers and scientists within the field of research of your study (Hossain, Gedeon &  Sankaranarayana, 2017). In addition to this, every research project must introduce some gaps in its research wok in order to maintain the future growth possible in that particular context. In addition to this, these gaps let the researcher do the collection of piece of information that they have left during the research work or not mentioned within any scientific literature.

The goal and aim of the concerned literature, more specifically within the experiment done was to present one study that finds a classifier and feature selection method for indentifying observer’s GSR features for predicting the hidden mental state of any person within any video (displayer). This experiment mainly aimed at the discrimination process of happy smiles and other kinds (Hossain, Gedeon &  Sankaranarayana, 2017). The observers were 25 to 39 year old participants those who have different kinds of emotional state of mind and different responses towards same video clips about smiles.

The identification of drawback or gaps of this literature is difficult in comparison with other literature elaborated about this facial expression discrimination as there are no present literature that incorporated GSR signals for discriminating the real and fake smiles with the help of GSR signals. The experiment incorporated five features selection methods for identifying the fake and real smile, such as “being k-nearest neighbor (KNN), support vector machine (SVM) and simple neural network (NN) and two binary classifiers” (Hossain, Gedeon &  Sankaranarayana, 2017).

In contrast with these five features the previous literatures used the GSR signals for discriminating between displayers. This concerned experiment has used the GSR signals for managing discriminating the stress being imposed on faces for fake and real smiles. The probabilistic neural network and KNN were 70% and 70.8% but the accuracy of discrimination was only achieved with the help of SFFS based GSR signals and that was 79.5%. Here the gap was identified that the signals did not play the lead role in identifying the responses coming from human faces (Hossain, Gedeon &  Sankaranarayana, 2017). The curve fitting models helped and found the stress differences among human and the discrimination was successful and that was 91.4%.

In addition to these facts, there is another gap that was addressed by neither the experiment nor the literature. This is use of mobile application for managing the article has chosen this advancement as their future developmental perspective. Therefore, this can be identified as the gap involved within this literature. Mobile application would be one better option for monitoring the displayers in order check the accuracy of smiles among participants that detects fake and real smiles among them with respect to variable situations and conditional aspects (Hossain, Gedeon &  Sankaranarayana, 2017). The GSR signals would be the main advancement used in mobile application as the KNN, SBBS and other included features will be less recommended for that aspect. The GSR signals can directly identify the state of stress given to human face due to any video clip that they experienced by their visuals.

Therefore these gaps are identified within this literature as well as in this particular experiment in order to manage experimental perspective. Resolution process to reduces this gaps will results into the further development in this segment of operation that leads to identification of fine and effective stress elements on human faces that helps in identifying the fake and real smiles among participant’s faces.

5. Conclusion

This can be concluded that the psychological responses collected from different emotional states of mind can be collected and used for doing research on the field of recognition of human emotional state. The facial expression is considered as one tool for innovating various application for improving the technological domain. In contrast with these facts, there are certain examples for using facial expressions, such as security checks using facial expressions, and detection of mental health of psychologically misbalanced people.

Therefore, the measurement and identification of psychological state of human has become very important for knowing the change of behavior among people with respect to various situational changes among them. In addition to this, from the point of view of human comfort has become one mandatory perspective in technically sound era. This factor is mandating all developmental perspectives involved within technical innovations.

This report has elaborated about the functionality of the emotional state detection and its usages for research cases. In addition to this, one literature is concerned in this report for understanding the usages of emotional state detection of human for understanding their behaviors. In addition to this, the author of this article has considered Galvanic Skin responses for creating stimulations of smiley faces. The GSR signals are transferred through various stages in order to test the emotional state of mind that is raised because of changes in visuals.  In accordance with these perspectives, these galvanic skin responses are recorded for observations from a group of observers who watches 5 real and 5 posed smile responses on screen and then their responses are recorded and examined for understanding the mental strength as well as behavioral changes in accordance with real and fake smile cases. This concerned research article is critical evaluated within this report. In addition to this, the critical review of the article has also considered the strengths of the article as well as it is elaborating about key point evaluation involved within this research paper.

The third segment of this report has reviewed on three significant articles related to the concerned research article within this report. These three literature review section is providing one brief summary of the literatures and also the relations with the concerned research paper is also elaborated within this report. The comparative analysis based on the emotional state detection among human helps the researcher in understanding the future of this particular aspect in this contemporary era of technological development.

In contrast with these facts, gaps involved within the concerned literature are also elaborated within this report in order to highlight the drawbacks of research involved within this research process. These gaps not only highlights the drawbacks of the research but also shows the way for further development of this technologically sound experiment for identifying real and fake smiles among human that can easily state the human behavior and their complexity towards situations they face in their life.

References 

Abbas, S.M., 2016. The role of Computer in Emotional Detection for Education and Health. International Journal, 4(1).

Bartlett, M.S., Littlewort, G.C., Frank, M.G. & Lee, K., 2014. Automatic decoding of facial movements reveals deceptive pain expressions. Current Biology, 24(7), pp.738-743.

Bernstein, M.J., 2016. Research in Social Psychology: Consequences of Short-and Long-Term Social Exclusion. In Social Exclusion (pp. 51-72). Springer International Publishing.

Bryant, G.A. & Aktipis, C.A., 2014. The animal nature of spontaneous human laughter. Evolution and Human Behavior, 35(4), pp.327-335.

Calvo, M.G., Gutiérrez-García, A., Avero, P. & Lundqvist, D., 2013. Attentional mechanisms in judging genuine and fake smiles: Eye-movement patterns. Emotion, 13(4), p.792.

Calvo, M.G., Marrero, H. & Beltrán, D., 2013. When does the brain distinguish between genuine and ambiguous smiles? An ERP study. Brain and cognition, 81(2), pp.237-246.

Claypool, H.M. & Bernstein, M.J., 2014. Social exclusion and stereotyping: Why and when exclusion fosters individuation of others. Journal of personality and social psychology, 106(4), p.571.

Cosentino, S., Sessa, S. & Takanishi, A., 2016. Quantitative Laughter Detection, Measurement, and Classification—A Critical Survey. IEEE reviews in biomedical engineering, 9, pp.148-162.

Dawel, A., Palermo, R., O’Kearney, R. & McKone, E., 2015. Children can discriminate the authenticity of happy but not sad or fearful facial expressions, and use an immature intensity-only strategy. Frontiers in psychology, 6.

Duijn, J.V., 2014. Real-time Laughter on Virtual Characters (Master’s thesis).

Gutiérrez-García, A. & Calvo, M.G., 2015. Discrimination thresholds for smiles in genuine versus blended facial expressions. Cogent Psychology, 2(1), p.1064586.

Gutiérrez-García, A. & Calvo, M.G., 2016. Social anxiety and perception of (un) trustworthiness in smiling faces. Psychiatry Research, 244, pp.28-36.

Hehman, E., Leitner, J.B., Deegan, M.P. & Gaertner, S.L., 2013. Facial structure is indicative of explicit support for prejudicial beliefs. Psychological science, 24(3), pp.289-296.

Hernandez, J. & Picard, R.W., 2014, October. SenseGlass: using google glass to sense daily emotions. In Proceedings of the adjunct publication of the 27th annual ACM symposium on User interface software and technology (pp. 77-78). ACM.

Hossain Md. Z., Gedeon T., &  Sankaranarayana R.,  2017. Observer’s Galvanic Skin Response for Discriminating Real from Fake Smiles. [online] Available at: https://business.uow.edu.au/content/groups/public/@web/@bus/documents/doc/uow223900.pdf [Accessed 9 Apr. 2017].

Iwasaki, M. & Noguchi, Y., 2016. Hiding true emotions: micro-expressions in eyes retrospectively concealed by mouth movements. Scientific reports, 6.

Knapton, H.M., Bäck, H. & Bäck, E.A., 2015. The social activist: conformity to the ingroup following rejection as a predictor of political participation. Social Influence, 10(2), pp.97-108.

Knowles, M.L., 2014. Social rejection increases perspective taking. Journal of Experimental Social Psychology, 55, pp.126-132.

Kunstman, J.W., Tuscherer, T., Trawalter, S. & Lloyd, E.P., 2016. What lies beneath? Minority group members’ suspicion of Whites’ egalitarian motivation predicts responses to Whites’ smiles. Personality and Social Psychology Bulletin, 42(9), pp.1193-1205.

LaCosse, J., Tuscherer, T., Kunstman, J.W., Plant, E.A., Trawalter, S. & Major, B., 2015. Suspicion of White people’s motives relates to relative accuracy in detecting external motivation to respond without prejudice. Journal of Experimental Social Psychology, 61, pp.1-4.

Ma, L. & Lillard, A.S., 2013. What Makes an Act a Pretense One? Young Children’s Pretend-Real Judgments and Explanations. Child Development Research, 2013.

Monkaresi, H., 2014. Recognising Complex Mental States from Naturalistic Human-Computer Interactions.

Müller, S., Jusyte, A., Trzebiatowski, S., Hautzinger, M. & Schönenberg, M., 2016. Processing of Ambiguous Facial Affect in Adolescents with Depressive Symptoms Prior to and Following Social Exclusion: The Role of Perceptual Sensitivity and Response Bias. Journal of Psychopathology and Behavioral Assessment, pp.1-11.

Paracampo, R., Tidoni, E., Borgomaneri, S., di Pellegrino, G. & Avenanti, A., 2016. Sensorimotor network crucial for inferring amusement from smiles. Cerebral cortex.

Sacco, D.F., Merold, S.J., Lui, J.H., Lustgraaf, C.J. & Barry, C.T., 2016. Social and emotional intelligence moderate the relationship between psychopathy traits and social perception. Personality and Individual Differences, 95, pp.95-104.

Shoda, T.M. & McConnell, A.R., 2013. Interpersonal sensitivity and self-knowledge: Those chronic for trustworthiness are more accurate at detecting it in others. Journal of Experimental Social Psychology, 49(3), pp.440-443.

Song, R., Over, H. & Carpenter, M., 2016. Young children discriminate genuine from fake smiles and expect people displaying genuine smiles to be more prosocial. Evolution and Human Behavior, 37(6), pp.490-501.

Tuscherer, T., Sacco, D.F., Wirth, J.H., Claypool, H.M., Hugenberg, K. & Wesselmann, E.D., 2015. Responses to exclusion are moderated by its perceived fairness. European Journal of Social Psychology.

Wang, J., Li, W., Li, X., Li, P., Zhang, Y., Jia, X., Chen, Y., Vanhoy, M. & Sun, B., 2016. A differing bidirectional impact on the recognition accuracy of facial expression. International Journal of Psychology.

Wesselmann, E.D., Hales, A.H., Ren, D. & Williams, K.D., 2015. A temporal need threat framework. Handbook of personal security, pp.191-205.

Wojciechowski, J., Stolarski, M. & Matthews, G., 2014. Emotional intelligence and mismatching expressive and verbal messages: A contribution to detection of deception. Plos one, 9(3), p.e92570.

Young, S.G. & Lamson, W., 2016. Task framing reduces emotion decoding negativity biases in social anxiety. Journal of Applied Social Psychology, 46(10), pp.607-614.

Order an Essay Now & Get These Features For Free:

Turnitin Report

Formatting

Title Page

Citation

Outline

Place an Order