Google recently developed a technology that can detect human emotions in a 2 X 2 dimension (energy level and body movement). What are some of the products you can build using that technology? List a few ideas, then choose one and design the product for that idea.

1. CLARIFY:
   1. Are we limited to a specific platform? Assume it's my choice.
   2. Are we focused on a specific type of user? Assume it's my choice.
   3. Is it OK to assume that Google wants to build any app on it's own v. partner with an existing application? Assume it's my choice.
   4. Are there any limitations to the technology (ex. it only works on a specific type of device, the user must be doing XYZ, etc.)? Assume it's open to my interpretation.
2. HIGH LEVEL USE CASES FOR TECH:
   1. Yoga / Meditation App: App that tracks your energy level and body movements during yoga and allows you to see how your emotions change during your sessions. Focus on stress relief via yoga / meditation for the user.
   2. Mental Health App: App that tracks user's emotions during the day based on their energy level and body movement. Helps them better mental health.
   3. Mental Diagnostic App: App that allows doctors / psychiatrists / psychologists to diagnose mental health problems. 
   4. Medical Research App: App that allows researchers more insight into human emotions for medical research (ex. mental health diseases, the importance of exercise, etc.)
3. SELECT ONE USE CASE: Given mental health has become an important topic during COVID with people feeling more isolated, I'd like to focus on the Mental Health App, which likely has a large user base / can address important current user needs now.
4. PRODUCT DESIGN:
   1. USER GROUPS: We can break down user groups by age:
      1. Kids / Teens: 0 - 18 years old
      2. Young Adults: 19 - 40 years old 
      3. Old Adults: 41 - 65 years old
      4. Senior Citizens: 65+ years old
   2. SELECT USER GROUP: I'd like to focus on the Young Adults segment, as they are likely to be more comfortable using new technology and I believe the app I design will focus on mobile / wearable technology. (More specifications to come.)
   3. USER NEEDS: I'd like to list high level user needs in regards to their emotions / mental health.
      1. DEAL WITH STRESS: I need a way to deal with stress and anxiety from school / work / life in general.
      2. ISOLATED: I need a way to feel less isolated / more connected to others. 
      3. POSITIVE BEHAVIORS: I need a way to learn what are positive behaviors I can do to help with my mental health.
      4. MENTAL HEALTH RESOURCES: I need access to mental health professionals and other resources (like books).
   4. USER PAINPOINTS: From the user needs, I'd like to specify painpoints associated with each of the needs.
      1. DEAL WITH STRESS: 
         1. I don't know what resources are there to help me. 
         2. There are too many options online, and I dont know what is best for me. 
      2. ISOLATED: 
         1. I feel like I am alone. I find it hard to make new connections.
         2. I have a hard time sharing my feelings with others.
      3. POSITIVE BEHAVIORS: 
         1. I don't know what triggers positive v. negative emotions. 
         2. I need a way to stop repeating bad behavior that affects my mental health negatively. 
      4. MENTAL HEALTH RESOURCES: 
         1. I don't know who reputable therapists are.
         2. I don't know if I need to see a therapist.
         3. I cannot afford therapy.
   5. PRIORITZE PAIN POINTS: 

      1. Painpoint	Impact to User	Notes
         I don't know what resources are there to help me.	Low	Lots of resources online
         There are too many options online, and I dont know what is best for me.	High	Lots of resources online but search can be overwhelming
         I feel like I am alone. I find it hard to make new connections.	Medium	Likely only affects a portion of the population.
         I have a hard time sharing my feelings with others.	Medium	Likely only affects a portion of the population.
         I don't know what triggers positive v. negative emotions.	High	Unaware that certain behaviors trigger emotions.
         I need a way to stop repeating bad behavior that affects my mental health negatively.	High	May be aware of behaviors but stopping them can be difficult.
         I don't know who reputable therapists are.	Medium	Therapist online reviews available but may be difficult to find one you're comfortable with.
         I don't know if I need to see a therapist.	High	Many may not know they need therapy to help with mental health problems.
         I cannot afford therapy.	Low	Free clinics etc likely available

   6. SOLUTIONS: I want to focus on painpoints that have high impact to the user. 

      1. #	Pain Point	Solution
         1	There are too many options online, and I dont know what is best for me.	App that reads your emotions and surfaces best mental health resources / therapists based on your needs.
         2	I don't know what triggers positive v. negative emotions.	App that tracks your body movement and energy level to read your emotions. When your emotions are bad, it notifies you / tracks that data.
         3	I need a way to stop repeating bad behavior that affects my mental health negatively.	App that reads emotions and offers alternative suggestions to combat bad behavior. For example, "I see you are overall happier when you take a morning walk. Today it looks like you're feeling blue. Why don't you go outside for a walk?"
         4	I don't know if I need to see a therapist.	App that reads emotions and suggests when you need a therapist based on sustained patterns that suggest a user has a mental health problem, like depression. Provides therapist recommendations.

      2. Given that #1 and #4 are similar, I'd combine them. #2 and #3 are also similar, and there's the possibility to start with #2 as a MVP build with features of #3 to follow. You could even use aspects of #1/#4 for that post MVP solution as well. (See solution deep dive.) I'd like to focus building #2 as the initial solution, because it really takes advantage of Google's technology and allows a user to directly gain insight into what behaviors are triggering changes in mood, which is the first step towards working on mental health. 
   7. SOLUTION DEEP DIVE: The initial build of this app would focus on a mobile device build (assuming the technology works on a mobile device) but has large applications in the wearables area. In the ideal state, there would be a mobile app that surfaces the tracking data (described below) but body movement and energy level could be tracked automatically on a user's watch. (Long term, there may even be implications on voice too. For example, do certain tones indicate a user's emotion.)
      1. MVP: 
         1. Build an app that tracks the energy level and body movement of the user, which then shows what their emotions are at that time. 
         2. User has the ability to log their energy level (ex. high, medium, low, very low, etc.) and their body movement (which may be automated) given mobile devices can track movement (like steps).
         3. User sees emotional tracker of their mood throughout the day based on their data inputs.
         4. When their mood falls into any high / low area, the user is notified and has the ability to log what they're doing. For example, if the app detects the user is feeling sad, the user can log what caused their feeling of sadness / what they were doing.
      2. POST MVP: 
         1. With enough data, the app can predict user's mood / encourage the user to do positive behavior that enforces good emotions. (Ex. go for a walk today.)
         2. Based on the user's emotional state, the app could surface personalized recommendations on mental health resources / therapists. 
         3. App could automate the log of energy level with a corresponding wearable app (for example, app for the Apple Watch) that could automatically detect a user's energy level and movement.
   8. SUMMARY: Using Google's new technology to detect human emotions through energy level and body movement, I'd build an app that allows a user to track their mental health by logging their energy level and body movement (ideally would be automated). They could see how their behaviors affect their mood and eventually get recommendations on how to do actions that will encourage a positive mindset. 

I would structure my answer as follows:

 

1. Clarifying the question

What could I do if Google had developed a technology that measures energy levels and motion to detect a user’s emotions?

 

2. Brainstorm possible products that could leverage this technology

• An app that detects your pets emotions so that as a pet owner, you can better understand/care for your pet 

• An app that detects elderly people who have issues communicating with their loved ones 

• A tool to help therapists understand how patients, particularly children, really feel about a specific issue during a therapy session 

• A wellness app that recommends yoga, meditation techniques and diet tips based on users’ current mood/emotions 

 

3. Focus on one idea and develop a product for it 

I am choosing to design a product for the last idea: a wellness app that recommends yoga, meditation techniques and diet tips based on users’ current mood/emotions 

 

This product would be integrated as a new app for an existing wearable product, like Google Watch for example. It would use a number of user data including energy levels and motion to detect the user’s current set of emotions, and which of these emotions is prevalent at a given point. 

I would focus on negative/challenging emotions, since this is the type of situation where a user would want to feel better and improve their mood. 

I’d start with a list of the 6 basic emotions, which could be expanded upon later based on initial data:

• Feeling sad 

• Feeling angry  

• Feeling afraid  

• Feeling anxious  

• Feeling fatigued

• Feeling bored 

 

Some use cases where I envision the app being used:

• User feeling afraid during a flight 

• User feeling anxious before a job interview 

• User feeling sad after receiving difficult news 

• User feeling angry after a bad day at work 

 

The user would open the app and be presented with an emotional evaluation detailing how the user is feeling, what the prevailing emotions are, and presenting recommendations based on the user’s contextual preferences in that particular moment.

There would be 3 main sections for the user to pick based on their context and goals:

1. Meditation sessions (specific goals and lengths available based on user’s preferences)  

2. Yoga sessions (different goals and lengths available based on user’s preferences)  

3. Diet recommendations (different type of recipes/snack suggestions based on season and time of day)

 

Over time, the app would gather and analyze both qualitative and quantitative data in order to optimize and personalize recommendations for the user:

• Quantitative feedback: the app itself would measure the effectiveness of these recommendations by tracking any change in the user’s emotions, and present these changes to the user as a feedback loop mechanism  

• Qualitative feedback: 

  • users can rate/share most useful/effective content for qualitative feedback 

  • User can save most useful/effective content for easy access in the future 

 

4. How would I measure success?

• Like any app, I would look DAU/WAU/MAU to understand how engaging and effective the app is in driving users to engage with it regularly 

• To understand the app effectiveness, in addition to ratings and engagement metrics, I would measure how the user’s emotions change after the user engages with the app (E.g. can we see a decrease in negative emotions after the user engaged in a meditation session to manage their fears?)

 

Google recently developed a technology that can detect human emotions in a 2 X 2 dimension (energy level and body movement). What are some of the products you can build using that technology? List a few ideas, then choose one and design the product for that idea.

Just to reiterate, google developed a technology that can detect human emotions based off of energy level and body movement. I would ask clarifying questions as to how this technology works. Does it require special cameras? Does it require a user to actually turn it on? What’s the level of confidence in the results? Does the user need to opt in to this program? What kind of human emotions are we talking about?

Assuming that the user does need to opt in, but it works off of a normal laptop or phone camera and does need to be turned on, I would start brainstorming ways that this might help solve an existing user issue.

– This app might be useful when it comes to detecting fatigue and general tiredness when working. Google could offer a product that would remind users when to go for some air or take a walk whilst working
– Emotions is useful to gauge how a user feels about any particular product. This would be especially useful for both the user and the app to understand how to optimize UI/UX, product placement, etc.
– Emotions would be useful for Youtube, where it can better hone in on video recommendations than a simple Thumbs up or Thumbs Down.

I want to actually build for number 3, because a better recommendation system would be kind of amazing.

The goal of this feature is to deliver a better recommendation system for users who opt-in to this technology.

The way we know the recommendation is working is by longer viewing times on Youtube, a general happier user from the emotion technology, and better retention.

The problem we are trying to solve for our users is how to elevate more relevant content so that they are able to watch more videos that are akin to their interests. Understand that their interest may change everyday. Some key features for this would be:

– Users would need to opt-in and sync their face and camera up to make sure they work. There will also need to be an opt-in everytime a user surfs over to Youtube.
– A backend database that tracks videos you’ve watched and also the change in emotion from the beginning of the video and through the end
– A front-end display showing the users how their emotions have changed throughout the video itself
– Asking the users how they really felt about the video compared to the emotion captured from the technology
– A algorithm that can match your personal preferences with your emotional response for the next video you want to watch.

Within the algorithm, there’s a lot more features that we can build. Like what does emotions tell us? What does each of the four grids really mean in terms of how they feel about a particular video? I think that’s why we pare it with the actual ratings the user provides to inform us how to move forward.

All of the bullet points would be key to the first launch as it provides us with all the information we need to continue to iterate on the recommendation engine. We will know the recommendation engine is working when we pare a level of internal confidence metric with the user’s actual rating. Also through traditional metrics like how many videos are the users watching one after another.

In summary, I would leverage the emotion engine that Google created to deliver better recommendations for users on Youtube. At first launch, we should take care of all user privacy concerns by making it opt-in and then gather data both through the technology and with user input to help our machine learning algorithm produce better results in the future.