Highlights

The inclusion of content related data, such as analysing the type of sentiment in communication, can understandably raise concerns regarding individual privacy. This can be effectively addressed by encrypting the data at the source (thereby rendering the content indecipherable) and aggregating the reporting at team level (typically, 10 people and above) so that individuals cannot be identified.

When these security and privacy controls are applied, the results from the analysis are reported on the basis of summarised and anonymised team patterns, which protect privacy whilst providing valuable insight into the sentiment and level of psychological safety being experienced by teams.

In this case, our analysis focused on the ratio of positive and negative sentiment. Perhaps somewhat counterintuitively, a disproportionate amount of positive sentiment can reflect an increased level of fear. When people fear speaking up or calling out bad news, the general sentiment is typically skewed towards the positive. Whilst there is nothing wrong with positive sentiment per se, an appropriate balance of positive and negative sentiment means that people are more likely to speak up because they are also in the habit of expressing concerns. This balance of positive and negative sentiment reflects the use of “honest language”.

Highlights

The analysis initially focused on identifying the behavioural drivers of the Fair Allocation of Work, which included:

• Trust: The level of trusted leadership and the trust climate throughout the workplace.
• Respect: The level of mutual respect, courtesy, equity and honesty within the workplace.
• Opportunity: The amount of fair recruitment, allocation of duties and responsibilities.
• Learning: The effectiveness of the learning and development and mentoring environment.
• Collaboration: The degree of inclusive leadership and effective communication.

GalaxyLens measured and predicted the existence and extent of these drivers at team levels throughout the organisation and identified hot spots and areas requiring attention.

Highlights

The typical assessment of team dynamics relies on surveys that are filled out at a point in time by team members completing a task. Whilst this can provide valuable insight, surveys of this type can also be subject to significant behavioural biases in the interpretation of team dynamics. GalaxyLens was deployed to automatically and predictively measure the level of team synergy on a continuous basis.

This involved the analysis of digital communication patterns to determine how much people are in sync and share the same flow. Even when they are physically separated as in hybrid working environments. Synergy proved to be particularly effective at enhancing the collaboration between office and working from home teams.

It was found that the more aligned people are in their organisational network positions and more correlated in the type of communication interaction, the higher the level of synergy.

Highlights

Our technology used convolutional neural networks (CNNs) to employ facial emotion recognition (FER). In particular, we focused on six different emotions ranging from anger, fear, happiness, neutrality, sadness, and surprise. The FER analysis was complemented with survey feedback from the audience viewing people speaking and/or presenting in meetings. The combination of FER and survey data demonstrated the following behavioural features of videoconferencing meetings:

• The happier the speaker, the happier and less neutral the audience - high neutrality does not reflect an engaged audience. 
• The more neutral the speaker, the less surprised the audience - higher levels of surprise keep an audience engaged. 
• When the audience experience a broad range of emotions with wide fluctuations in happiness and fear, they scored the presentation the highest. Neutral faces tend to indicate boredom and are negatively correlated with the high scores. The appearance of fear on the faces of the audience correlates positively with the perceived quality of the presentation.
• Presenters achieve the most engaged audience and obtain the highest score when they smile and display a happy face. Happy presenters will also reduce neutral faces among the audience and fewer neutral faces is associated with a higher presentation score.

Trying to provide “unlimited bliss” by keeping the audience constantly happy is not the best method for high-quality video presentations. Rather, a good presenter needs to challenge the audience by puzzling it and providing unexpected and even temporarily painful information, which then will be resolved over the course of the presentation. At the same time, the presenter should display a positive attitude to convey enthusiasm and positive energy to the audience.

Where meetings are more interactive and focused on processes and actions, turn-taking and allowing everyone to provide input are more constructive.