2,541 Hits in 3.4 sec

Using artificially generated pictures in customer-facing systems: an evaluation study with data-driven personas

Joni Salminen, Soon-gyo Jung, Ahmed Mohamed Sayed Kamel, João M. Santos, Bernard J. Jansen
2020 Behavior and Information Technology  
We conduct two studies to evaluate the suitability of artificially generated facial pictures for use in a customer-facing system using data-driven personas.  ...  STUDY 2 examines the application of artificially generated facial pictures in data-driven personas using an experimental setting where the highquality pictures are implemented in persona profiles.  ...  It would be important to investigate if the generated pictures involve an algorithmic biasgiven that the training data may be biased, it would be worthwhile to analyze how diverse the generated pictures  ... 
doi:10.1080/0144929x.2020.1838610 fatcat:ubsgdxjeq5bd3ebki5rf4qzoay

Countenancing Employment Discrimination

Kerri A. Thompson
2020 Texas A&M Law Review  
Then, it analyzes whether the use of facial recognition technology in background checks violates Title VII under the disparate impact theory of liability due to the known issue of skewed data sets and  ...  The very technological breakthroughs that made facial recognition technology commercially viable—data compression and artificial intelligence— also contribute to making facial recognition technology discriminatory  ...  See Larry Hardesty, Study Finds Gender and Skin Type Bias in Commercial Artificial Intelligence Systems, MIT NEWS (Feb. 11, 2018), study-finds-gender-skin-type-bias-artificial-intelligence-systems  ... 
doi:10.37419/lr.v8.i1.2 fatcat:4ponsegykrajpk4svu3whgnl2e

Machine Bias: Artificial Intelligence and Discrimination

Can Yavuz
2019 Social Science Research Network  
Many problems in the field stem from lack of regulation and over-reliance on artificial intelligence.  ...  The findings reveal that artificial intelligence discriminates in various ways, and the most vulnerable and discriminated groups are more likely to be victims of it.  ...  The bigger picture, a comparison of demographics of sentenced prison population and general population demographics, shows the gravity of the problem.  ... 
doi:10.2139/ssrn.3439702 fatcat:54zv7vvppne7dn6gcfh3phxt5e

Emotional Expression of #body on Instagram

Clelia Malighetti, Simona Sciara, Alice Chirico, Giuseppe Riva
2020 Social Media + Society  
A total of 500 Instagram photos marked by specific hashtags related to body image components were analyzed and specific discrete emotions expressed in each picture were detected using the Emotion application  ...  Our aim was to explore emotions in Instagram images marked with hashtags referring to body image–related components using an artificial intelligence–based discrete emotional analysis.  ...  According to previous studies on positive bias and positive valence on Instagram, hashtags in general were mostly related to positive emotions (vs. negative ones). 2.  ... 
doi:10.1177/2056305120924771 fatcat:4zg6frbmpjd47ekyi4xwjra3xy

Exploring the Intersection of the Digital Divide and Artificial Intelligence: A Hermeneutic Literature Review

Lemuria Carter, University of New South Wales, Dapeng Liu, Caley Cantrell, University of New South Wales, Virginia Commonwealth University
2020 AIS Transactions on Human-Computer Interaction  
Given the rapid advancements in information communication technology (ICT), researchers and practitioners need to understand the impact that emerging phenomena, such as artificial intelligence (AI), have  ...  We propose three theoretical framings: 1) conceptualizing the divide, 2) modeling the divide, and 3) analyzing the divide.  ...  Also, AI can generate decisions from training data, which may comprise biased observations.  ... 
doi:10.17705/1thci.00138 fatcat:yxm2rkkctzdcvcb3pxtzg46rx4

Read My Face: Automatic Facial Coding Versus Psychophysiological Indicators of Emotional Valence and Arousal

T. Tim A. Höfling, Antje B. M. Gerdes, Ulrich Föhl, Georg W. Alpers
2020 Frontiers in Psychology  
We tested the sensitivity of a well-established automatic facial coding software program to detect spontaneous emotional reactions in individuals responding to emotional pictures.  ...  Researchers are now able to decode emotional facial expressions with impressive accuracy in standardized images of prototypical basic emotions.  ...  bias.  ... 
doi:10.3389/fpsyg.2020.01388 pmid:32636788 pmcid:PMC7316962 fatcat:etpvtkdzkvebzbbr6fmqunbnq4

What Twitter Profile and Posted Images Reveal About Depression and Anxiety [article]

Sharath Chandra Guntuku, Daniel Preotiuc-Pietro, Johannes C. Eichstaedt, Lyle H. Ungar
2019 arXiv   pre-print
For depression, we find that profile pictures suppress positive emotions rather than display more negative emotions, likely because of social media self-presentation biases.  ...  with users' depression and anxiety, controlling for demographics.  ...  We control for age and gender using partial correlation so that our analysis is not skewed by any potential demographic bias in the data.  ... 
arXiv:1904.02670v1 fatcat:n47ojpricbb3jdh2cnqspcz4aq

Characterizing consumer emotional response to sweeteners using an emotion terminology questionnaire and facial expression analysis

K.A. Leitch, S.E. Duncan, S. O'Keefe, R. Rudd, D.L. Gallagher
2015 Food Research International  
Facial 44 expression responses were recorded in the first session of both days using FaceReader 5.0 and 45 individual participant videos were analyzed per sample for 5-sec post-consumption (α=0.05) in  ...  More research exploration related to emotions and food is 57 needed in order to accrue a more accurate picture of consumer product preferences. 58 59  ...  Facial expression data for water was analyzed as a "sample" in 239 11 comparison to the sweetened tea samples in each category and also as a baseline, where its post-240 consumption mean was subtracted  ... 
doi:10.1016/j.foodres.2015.04.039 fatcat:qo3veixgejhdtfdhb6gsdvicee

Assessing the Effectiveness of Automated Emotion Recognition in Adults and Children for Clinical Investigation

Maria Flynn, Dimitris Effraimidis, Anastassia Angelopoulou, Epaminondas Kapetanios, David Williams, Jude Hemanth, Tony Towell
2020 Frontiers in Human Neuroscience  
In line with this general trend, inter-disciplinary approaches have been taken to automate the recognition of emotions in adults or children for the benefit of various applications, such as identification  ...  and, to some extent, the resurrection of Artificial Intelligence (AI).  ...  Generally speaking, there are two sources of bias to be prevented: (a) data sources and input, (b) algorithms (Hajian and Bonchi, 2016) .  ... 
doi:10.3389/fnhum.2020.00070 pmid:32317947 pmcid:PMC7156005 fatcat:7zsczgvigrbi3hn7yop6jyibtq

The Contribution of the Lower Third of the Face to Perceived Age: Do Masks Make You Appear Younger?

Peter J Nicksic, Alison M Karczewski, Qianqian Zhao, Nicholas A Garcia, Brett F Michelotti, Ashish Y Mahajan, Samuel O Poore
2021 Aesthetic Surgery Journal Open Forum  
There is evidence that changes to the midface and lower third of the face in isolation contribute significantly to one's perception of overall facial age.  ...  Data were analyzed using PROC MIXED analysis. Results Masked patients on average appeared 6.17% younger (mean difference = 3.16 years, 95% CI = 2.26-4.06, P &lt; 0.0001).  ...  One study on the topic of facial subunits and aging found that artificially aging the lower third of the face in isolation made a patient appear 19.8% older (P < 0.0001). 13 While it is logical to assume  ... 
doi:10.1093/asjof/ojab017 fatcat:rmwxgbrtdfeqpcly2bhvqhgtj4

Associations between childhood maltreatment and emotion processing biases in major depression: results from a dot-probe task

Vivien Günther, Udo Dannlowski, Anette Kersting, Thomas Suslow
2015 BMC Psychiatry  
Conclusions: Our findings confirm the hypothesis that a mood-congruent bias in emotion processing observed in major depression is related to early traumatic experiences.  ...  Depression is characterized by mood-congruent cognitive biases, which play a crucial role in symptom persistence and recurrence.  ...  In general, the contradictory results for attentional biases to facial emotions as a function of childhood maltreatment might be explained by strong variations in sample characteristics such as age and  ... 
doi:10.1186/s12888-015-0501-2 pmid:26047613 pmcid:PMC4458030 fatcat:gczb7iqtrba6dgwevc7unoqiia

Atypical Social Judgment and Sensitivity to Perceptual Cues in Autism Spectrum Disorders

Baudouin Forgeot d'Arc, Franck Ramus, Aline Lefebvre, Delphine Brottier, Tiziana Zalla, Sanaa Moukawane, Frédérique Amsellem, Laurence Letellier, Hugo Peyre, Marie-Christine Mouren, Marion Leboyer, Richard Delorme
2014 Journal of Autism and Developmental Disorders  
Further studies on perceptual differences between photographs and synthetic pictures of faces might help understand atypical social judgment in ASD.  ...  A degraded sensitivity to facial perceptual cues might contribute to atypical social interactions in autism spectrum disorder (ASD).  ...  Participants' demographic characteristics are summarized in Table 1 .  ... 
doi:10.1007/s10803-014-2208-5 pmid:25149177 fatcat:4bdcjtdlinc4jj7hzsekcfpvzy

A Novel Method in Predicting Hypertension Using Facial Images

Lin Ang, Mi Hong Yim, Jun-Hyeong Do, Sanghun Lee
2021 Applied Sciences  
The data of 1099 subjects (376 men and 723 women) analyzed in this study were obtained from the Korean Constitutional Multicenter Study of Korean medicine Data Center (KDC) at the Korea Institute of Oriental  ...  In terms of facial colors, cheek color in men, as well as forehead and nose color in women, were the most distinct facial colors between the hypertension groups and normal individuals.  ...  Acknowledgments: We would like to thank Jong Yeol Kim for his support in this project. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app11052414 fatcat:voiz2e472jaaplqwqq4ogcb26a

Facial Reconstruction: A Systematic Review of Current Image Acquisition and Processing Techniques

Sam P. Tarassoli, Matthew E. Shield, Rhian S. Allen, Zita M. Jessop, Thomas D. Dobbs, Iain S. Whitaker
2020 Frontiers in Surgery  
A risk of bias assessment was also carried out on each study systematically using the respective tool in relation to the study in question.Results: From the initial 6,147 studies, 75 were deemed to fulfill  ...  Imaging techniques used in facial imaging come in many different modalities and sub-modalities which is imperative for such a complex area of the body; there is a clear clinical need for hyper-specialized  ...  Bias limitations: Medium risk of bias from the sequence generation, allocation concealment, and blinding (trial format study).  ... 
doi:10.3389/fsurg.2020.537616 pmid:33365327 pmcid:PMC7750399 fatcat:3mtr3sar7jde5m63wz4ajuedpu

Small-variance asymptotics for non-parametric online robot learning

Ajay Kumar Tanwani, Sylvain Calinon
2018 The international journal of robotics research  
During this master project, I could get an in-depth knowledge of how facial recognition systems and more generally biometric systems work. I got a sense of the impact of bias in such systems.  ...  Not all datasets have annotations for every type of bias. Generally, one dataset built specifically to analyse a type of bias will lack information in other types.  ... 
doi:10.1177/0278364918816374 fatcat:zmp3ojvbqvevxbzn4hccf5b26m
« Previous Showing results 1 — 15 out of 2,541 results