Your Face Mirrors Your Deepest Beliefs-Predicting Personality and Morals through Facial Emotion Recognition

Can we really "read the mind in the eyes"? Moreover, can AI assist us in this task? This paper answers these two questions by introducing a machine learning system that predicts personality characteristics of individuals on the basis of their face. It does so by tracking the emotional response of the individual's face through facial emotion recognition (FER) while watching a series of 15 short videos of different genres. To calibrate the system, we invited 85 people to watch the videos, while their emotional responses were analyzed through their facial expression. At the same time, these individuals also took four well-validated surveys of personality characteristics and moral values: the revised NEO FFI personality inventory, the Haidt moral foundations test, the Schwartz personal value system, and the domain-specific risk-taking scale (DOSPERT). We found that personality characteristics and moral values of an individual can be predicted through their emotional response to the videos as shown in their face, with an accuracy of up to 86% using gradient-boosted trees. We also found that different personality characteristics are better predicted by different videos, in other words, there is no single video that will provide accurate predictions for all personality characteristics, but it is the response to the mix of different videos that allows for accurate prediction.

Finding top performers through email patterns analysis

In the information economy, individuals' work performance is closely associated with their digital communication strategies. This study combines social network and semantic analysis to develop a method to identify top performers based on email communication. By reviewing existing literature, we identified the indicators that quantify email communication into measurable dimensions. To empirically examine the predictive power of the proposed indicators, we collected 2 million email archive of 578 executives in an international service company. Panel regression was employed to derive interpretable association between email indicators and top performance. The results suggest that top performers tend to assume central network positions and have high responsiveness to emails. In email contents, top performers use more positive and complex language, with low emotionality, but rich in influential words that are probably reused by co-workers. To better explore the predictive power of the email indicators, we employed AdaBoost machine learning models, which achieved 83.56% accuracy in identifying top performers. With cluster analysis, we further find three categories of top performers, "networkers" with central network positions, "influencers" with influential ideas and "positivists" with positive sentiments. The findings suggest that top performers have distinctive email communication patterns, laying the foundation for grounding email communication competence in theory. The proposed email analysis method also provides a tool to evaluate the different types of individual communication styles.

Aristotle Said "Happiness is a State of Activity" -- Predicting Mood through Body Sensing with Smartwatches

We measure and predict states of Activation and Happiness using a body sensing application connected to smartwatches. Through the sensors of commercially available smartwatches we collect individual mood states and correlate them with body sensing data such as acceleration, heart rate, light level data, and location, through the GPS sensor built into the smartphone connected to the smartwatch. We polled users on the smartwatch for seven weeks four times per day asking for their mood state. We found that both Happiness and Activation are negatively correlated with heart beats and with the levels of light. People tend to be happier when they are moving more intensely and are feeling less activated during weekends. We also found that people with a lower Conscientiousness and Neuroticism and higher Agreeableness tend to be happy more frequently. In addition, more Activation can be predicted by lower Openness to experience and higher Agreeableness and Conscientiousness. Lastly, we find that tracking people's geographical coordinates might play an important role in predicting Happiness and Activation. The methodology we propose is a first step towards building an automated mood tracking system, to be used for better teamwork and in combination with social network analysis studies.

Measuring the impact of spammers on e-mail and Twitter networks

This paper investigates the research question if senders of large amounts of irrelevant or unsolicited information - commonly called "spammers" - distort the network structure of social networks. Two large social networks are analyzed, the first extracted from the Twitter discourse about a big telecommunication company, and the second obtained from three years of email communication of 200 managers working for a large multinational company. This work compares network robustness and the stability of centrality and interaction metrics, as well as the use of language, after removing spammers and the most and least connected nodes. The results show that spammers do not significantly alter the structure of the information-carrying network, for most of the social indicators. The authors additionally investigate the correlation between e-mail subject line and content by tracking language sentiment, emotionality, and complexity, addressing the cases where collecting email bodies is not permitted for privacy reasons. The findings extend the research about robustness and stability of social networks metrics, after the application of graph simplification strategies. The results have practical implication for network analysts and for those company managers who rely on network analytics (applied to company emails and social media data) to support their decision-making processes.

Forecasting managerial turnover through e-mail based social network analysis

In this study we propose a method based on e-mail social network analysis to compare the communication behavior of managers who voluntarily quit their job and managers who decide to stay. Collecting 18 months of e-mail, we analyzed the communication behavior of 866 managers, out of which 111 left a large global service company. We compared differences in communication patterns by computing social network metrics, such as betweenness and closeness centrality, and content analysis indicators, such as emotionality and complexity of the language used. To study the emergence of managers' disengagement, we made a distinction based on the period of e-mail data examined. We observed communications during months 5 and 4 before managers left, and found significant variations in both their network structure and use of language. Results indicate that on average managers who quit had lower closeness centrality and less engaged conversations. In addition, managers who chose to quit tended to shift their communication behavior starting from 5 months before leaving, by increasing their degree and closeness centrality, the complexity of their language, as well as their oscillations in betweenness centrality and the number of "nudges" they need to send to peers before getting an answer.

Using four different online media sources to forecast the crude oil price

This study looks for signals of economic awareness on online social media and tests their significance in economic predictions. The study analyses, over a period of two years, the relationship between the West Texas Intermediate daily crude oil price and multiple predictors extracted from Twitter, Google Trends, Wikipedia, and the Global Data on Events, Language, and Tone database (GDELT). Semantic analysis is applied to study the sentiment, emotionality and complexity of the language used. Autoregressive Integrated Moving Average with Explanatory Variable (ARIMAX) models are used to make predictions and to confirm the value of the study variables. Results show that the combined analysis of the four media platforms carries valuable information in making financial forecasting. Twitter language complexity, GDELT number of articles and Wikipedia page reads have the highest predictive power. This study also allows a comparison of the different fore-sighting abilities of each platform, in terms of how many days ahead a platform can predict a price movement before it happens. In comparison with previous work, more media sources and more dimensions of the interaction and of the language used are combined in a joint analysis.