If Every Picture Tells A Story, AI Reads the Story Better than Humans
Have you ever looked at someone and thought, “I’ve got your number, friend?” It may be based on how a person presents him or herself, or a facial expression. Even a photo can lead to passing judgment on someone.
Researchers from two Moscow universities, National Research University Higher School of Economics (HSE) and Open University for the Humanities and Economics teamed up with a Russian-British business start-up called BestFitMe to train a cascade of artificial neural networks to make reliable personality judgments based on photographs of human faces. The model performed better than studies using machine learning or human raters.
The AI was able to make above-chance judgments about conscientiousness, neuroticism, extraversion, agreeableness and openness based on selfies the volunteers uploaded. The resulting personality judgments were consistent across different photographs of the same individuals. This information was posted in an article found at techxplore.com, written by researchers in Russia.
A sample of 12,000 volunteers who completed a self-report questionnaire measuring personality traits based on the “Big Five” model uploaded a total of 31,000 selfies for the study. The respondents were randomly split into a training and a test group. A series of neural networks were used to preprocess the images to ensure consistent quality and characteristics and exclude faces with emotional expressions, as well as pictures of celebrities and cats. Next, an image classification neural network was trained to decompose each image into 128 invariant features, followed by a multi-layer perceptron that used image invariants to predict personality traits.
Personalizing Targeted Sales Pitch
Recognizing personality from photos can help speed personality assessment for numerous uses, according to the researchers.
“Artificial intelligence can be used to propose products that are the best fit for the customer’s personality or to select the possible ‘best matches’ for individuals in dyadic interactions, such as customer service, dating or online tutoring,” the techxplore.com story says.
Studies asking human raters to make personality judgments based on photographs have produced inconsistent results, suggesting that their judgments are too unreliable to be used. Most people are predisposed to making flawed assessments of people from viewing their faces.
Recent evidence from neuroscience suggests that instead of looking at specific facial features, the human brain processes images of faces in a holistic manner.
read more at techxplore.com