Behavioral Segmentation For Experience Design

We track depression the wrong way.  We look for mood to improve first…  but that’s almost never how it works. Across both medication and therapy, the earliest signs of response  show up in function, not mood. And when patients expect “better mood first,”  it sets them up to think treatment isn’t working, even when it is. Here’s how I help patients track what actually changes first. The 5 functional signals that improve before mood 1) Sleep regulation  They’re falling asleep more easily or waking less often,  even if mood feels unchanged. 2) Energy and cognitive “lift”  Tasks feel less effortful.  They can initiate more, focus slightly better, or “think clearer.” 3) Predictability of the day  More consistent routines.  Less overwhelm.  Fewer emotional spikes. 4) Increased engagement  Showing up to therapy, texting a friend back,  getting out of the house more often. 5) Irritability drops  A subtle but powerful early marker.  Patients rarely notice this until you ask. Why this matters  If we help patients notice these shifts,  they’re less likely to abandon treatment too early. It reframes the work:  “You may not feel better yet,  but look at what’s already changing.” Bottom line  Mood is the last domino to fall.  Track function first — that’s where progress lives. I built Collaborative Psychiatry as a platform for high-yield learning on managing mental health in primary care and other busy outpatient settings. Check out the Collaborative Psychiatry QuickTakes podcast feed to get a sense of the learning available: https://lnkd.in/e5xrE_rm. How do you track early progress in depression treatment? 

𝗘𝗺𝗼𝘁𝗶𝗼𝗻𝗮𝗹 𝗠𝗮𝗽𝗽𝗶𝗻𝗴 𝘃𝘀. 𝗖𝘂𝘀𝘁𝗼𝗺𝗲𝗿 𝗝𝗼𝘂𝗿𝗻𝗲𝘆 : 𝗧𝗵𝗲 𝗕𝗮𝘁𝘁𝗹𝗲 𝗼𝗳 𝘁𝗵𝗲 𝗛𝗲𝗮𝗿𝘁 𝗮𝗻𝗱 𝘁𝗵𝗲 𝗪𝗮𝗹𝗹𝗲𝘁 I recently had a humorous debate with a startup founder in the medical retail space about the traditional 𝗖𝘂𝘀𝘁𝗼𝗺𝗲𝗿 𝗝𝗼𝘂𝗿𝗻𝗲𝘆 𝗠𝗮𝗽𝗽𝗶𝗻𝗴 of the step-by-step path from “𝘞𝘩𝘰 𝘢𝘳𝘦 𝘺𝘰𝘶?” to “𝘚𝘩𝘶𝘵 𝘶𝘱 𝘢𝘯𝘥 𝘵𝘢𝘬𝘦 𝘮𝘺 𝘮𝘰𝘯𝘦𝘺!” - and how it’s slowly fading. Pointed out that decisions are rarely driven by logic alone - 𝗲𝗺𝗼𝘁𝗶𝗼𝗻𝘀 𝗼𝗳𝘁𝗲𝗻 𝘁𝗮𝗸𝗲 𝘁𝗵𝗲 𝘄𝗵𝗲𝗲𝗹. That’s where 𝗘𝗺𝗼𝘁𝗶𝗼𝗻𝗮𝗹 𝗠𝗮𝗽𝗽𝗶𝗻𝗴 steps in, adding depth to the modern customer journey by capturing what customers 𝗳𝗲𝗲𝗹 at every step, not just what they 𝘥𝘰. 𝗦𝗼, 𝗪𝗵𝗮𝘁’𝘀 𝘁𝗵𝗲 𝗗𝗶𝗳𝗳𝗲𝗿𝗲𝗻𝗰𝗲? 𝗖𝘂𝘀𝘁𝗼𝗺𝗲𝗿 𝗝𝗼𝘂𝗿𝗻𝗲𝘆: Tracks actions - Click, Buy, Install, Complain, Repeat. Basically, it’s the 𝗚𝗼𝗼𝗴𝗹𝗲 𝗠𝗮𝗽𝘀 of user behavior. 𝗘𝗺𝗼𝘁𝗶𝗼𝗻𝗮𝗹 𝗠𝗮𝗽𝗽𝗶𝗻𝗴: Tracks 𝘧𝘦𝘦𝘭𝘪𝘯𝘨𝘴 - Excitement, Confusion, Frustration, Relief, Joy. Think of it as the 𝗦𝗽𝗼𝘁𝗶𝗳𝘆 𝗣𝗹𝗮𝘆𝗹𝗶𝘀𝘁 playing in their heads throughout the journey. 𝗪𝗵𝘆 𝗗𝗼𝗲𝘀 𝗘𝗺𝗼𝘁𝗶𝗼𝗻𝗮𝗹 𝗠𝗮𝗽𝗽𝗶𝗻𝗴 𝗠𝗮𝘁𝘁𝗲𝗿? Because no one remembers what they clicked. But they 𝗻𝗲𝘃𝗲𝗿 𝗳𝗼𝗿𝗴𝗲𝘁 𝗵𝗼𝘄 𝘆𝗼𝘂 𝗺𝗮𝗱𝗲 𝘁𝗵𝗲𝗺 𝗳𝗲𝗲𝗹, Clicks fade from memory, but emotions stick - kind of like the joy of finding extra onions in your biryani order! Refer Swiggy or Zomato. 𝗖𝘂𝘀𝘁𝗼𝗺𝗲𝗿 𝗝𝗼𝘂𝗿𝗻𝗲𝘆: 1. Search for food. 2. Select restaurant. 3. Place order. 4. Track delivery. 5. Eat happily. 𝗘𝗺𝗼𝘁𝗶𝗼𝗻𝗮𝗹 𝗠𝗮𝗽𝗽𝗶𝗻𝗴: 1. Hunger Craving – Excited! 2. Menu Browsing – Confused. Too many options! 3. Checkout Price – Shocked. Swiggy, why you do this? 4. Order Tracking – Anxiety. Why is the delivery guy circling ? 5. Food Arrives – Relief and Joy! 𝗛𝗼𝘄 𝘁𝗼 𝗖𝗼𝗺𝗯𝗶𝗻𝗲 𝗕𝗼𝘁𝗵? 𝗠𝗮𝗽 𝗘𝗺𝗼𝘁𝗶𝗼𝗻𝘀 𝘁𝗼 𝗔𝗰𝘁𝗶𝗼𝗻𝘀: Attach emotional states to each step of the customer journey. 𝗔𝗱𝗱𝗿𝗲𝘀𝘀 𝗣𝗮𝗶𝗻 𝗣𝗼𝗶𝗻𝘁𝘀 𝗙𝗶𝗿𝘀𝘁: Like adding “Cash on Delivery” for Indian parents who still don’t trust online payments. 𝗔𝗱𝗱 𝗘𝗺𝗼𝘁𝗶𝗼𝗻𝗮𝗹 𝗧𝗿𝗶𝗴𝗴𝗲𝗿𝘀: Surprise discounts or funny delivery updates - because who doesn’t love a “𝘠𝘰𝘶𝘳 𝘣𝘪𝘳𝘺𝘢𝘯𝘪 𝘪𝘴 𝘢𝘭𝘮𝘰𝘴𝘵 𝘩𝘰𝘮𝘦!” text? Customer Journeys tell you 𝘄𝗵𝗮𝘁 customers do. Emotional Mapping tells you 𝘄𝗵𝘆 they do it - and why they sometimes rage - quit in the middle. Combine both, and you’ll build products that customers don’t just use - they 𝗳𝗲𝗲𝗹 for. #productgyan #customersatisfaction #uiux #customerjourney #emotionalmapping #customerservice #productengineering

💡How To Capture Users' Emotions During User Research User research is a foundation for any product design process. The better you understand your target audience, the more chances you will succeed in building the right product for them. And capturing users' emotions is crucial for understanding how they feel about a product. Here are 4 UX techniques that can help you capture emotions: 1️⃣ Practice contextual inquiry. Observe users in their natural environment to see how they interact with the product and note their emotional responses 2️⃣ Use emotionally-focused questions during the interview. Include questions specifically designed to elicit emotional responses, such as "How did you feel when you used this feature?" 3️⃣ Do experience mapping. Track the entire experience of using the product, identifying key moments that trigger emotional responses (both positive and negative) 4️⃣ Create emotion-specific surveys. Utilize surveys designed to capture emotional responses, such as the PANAS (Positive and Negative Affect Schedule) or the SAM (Self-Assessment Manikin). ❗ Things to remember ✔ Use a think-aloud protocol to let users verbalize their thoughts and feelings as they interact with the product. ✔ Speak less, listen more. Give people time to express their thoughts. Ask follow-up questions to probe deeper into initial responses to uncover underlying emotions. ✔ Don't take words for granted. What people say might be different from what they really feel. Pay attention to users' body language for additional clues about their emotional state. ✔ Be mindful of surface-level responses (smiling and nodding). Users may smile and nod during the interview to be polite or conform to social norms, not necessarily because they agree or support what is being discussed. ✔ Users often hide criticism and tend to exaggerate positive feedback. It happens because they are uncomfortable expressing their true feelings.  ✔ Don't ask what people like or dislike (i.e., "What did you like about this experience?"). The response rarely matches the actual feelings of the user. ✔ Be mindful of bias. It's important to avoid making assumptions about users' thoughts and feelings based on superficial cues. The goal of UX research is to gain a deeper, more accurate insight into users unique contexts and needs. 📕 Guides and tools: ✔ Implementing Emotional Metrics in SaaS Products (by Odette Jansen) https://lnkd.in/dYaxWSVN ✔ User journey mapping, step by step https://lnkd.in/dNzt3NxX ✔ Feelings Wheel for Figma (by Christian Lunde)  https://lnkd.in/d8krqdcp 🖼️ The Spectrum of Empathy by NNGroup #UX #design #uxresearch #productdesign #design

I see nobody doing this with AI voice agents. So I did. This is unlocking a whole new layer of intelligence on your AI voice calls. What is it? Sentiment Anlalysis. Why does this matter? Because most businesses are sitting on a goldmine of voice data... but they’re not extracting the emotional signals that drive real outcomes. Here’s where sentiment analysis actually adds value: ✅ Customer Experience Monitoring Spot unhappy customers early. Trigger an automatic follow-up if a call turns negative. ✅ Agent Performance Tracking See how sentiment shifts across reps, scripts, or time. Is your team actually creating positive experiences? ✅ Trend Recognition Negative sentiment = higher churn? Now you've got predictive insights. ✅ Training & QA Flag poor sentiment calls for review. Let AI highlight the moments that caused friction. But it's not always worth your time... Sentiment analysis is useless if: → You're not acting on the data. → Your calls are too short or robotic. → You don’t have enough volume to find patterns. → Your domain needs custom sentiment tuning (sarcasm, mixed languages, etc.). Want to make it actually useful? Here’s how: → Link sentiment to outcomes like conversions or renewals. → Create real-time alerts or dashboards for your team. → Fine-tune the model on your transcripts, not generic ones. → Combine it with other signals like talk-time, interruptions, and keywords. The emotional layer of your calls is where the real insight lives. Curious how this works in practice? I’m happy to show what I built today. Drop a “curious” below or shoot me a message.

In UX, we talk a lot about what users think, but we rarely study how their attitudes actually change over time. Most research still relies on one-time surveys like SUS, NPS, or post-test ratings. These snapshots are useful, but they tell us almost nothing about how trust grows, how frustration accumulates, or how confidence rises and collapses after a single confusing update. Attitudes are not steady states. They are trajectories shaped by experience. There are scientific ways to track those trajectories. Continuous-Time SEM lets researchers measure how satisfaction or trust evolves in real time, even if we collect feedback at irregular moments. A streaming app can trigger a question after each session and see exactly when enjoyment starts to drop, so recommendations can intervene before disengagement sets in. Latent Transition Analysis helps us understand how people move between hidden states such as novice, intermediate, competent, or stuck. Instead of guessing who needs help in onboarding, we can calculate the probability a user will progress or remain frustrated and then redesign tutorials to move them forward. Bayesian Hierarchical Models solve a common UX problem. What if we do not have huge samples like consumer apps do? With twenty or thirty enterprise users, traditional statistics break down, but Bayesian methods still model growth and decline in attitudes. They can reveal that confidence improves for new employees but decreases for experts after a redesign, a pattern that would otherwise remain invisible. Joint Modeling goes further by connecting attitude trends with real outcomes such as churn. It can show that a drop in usability or motivation predicts cancellation two weeks before users actually leave, turning measurement into prevention. One of the most powerful and practical tools is Hidden Markov Modeling. Instead of relying on surveys, it infers emotional states from behavior like hesitation, rage clicks, repeated backtracking, or abandoned tasks. It detects frustration even when people are silent, revealing emotional shifts that traditional surveys fail to capture. If you want to go deeper into these methods and see more concrete examples, I put together a full breakdown on the blog. You can read it here: https://lnkd.in/eY_Nwme2

Why SexTech Needs Clearer Frameworks for Emotional Impact Testing View My Portfolio In the wellness space, emotional wellbeing is just as important as physical comfort. Yet many SexTech products are still tested primarily for mechanical performance—not for the emotional impact they have on users. As the industry matures, standardized frameworks for evaluating emotional response will become essential. Emotional impact testing can assess: • User comfort and anxiety levels during onboarding • Emotional readiness before sensory engagement • Moments of confusion, hesitation, or overwhelm • Overall sense of trust, safety, and predictability • Post-session emotional aftereffects, including calm or stress • Alignment with nervous system responsiveness and regulation Why emotional testing matters for the industry: • Creates more responsible, user-centered product design • Improves retention by identifying key emotional “drop-off” points • Helps brands differentiate from purely novelty-based competitors • Strengthens credibility with clinicians and wellness experts • Reduces the likelihood of overstimulation or negative experiences For businesses, emotional impact testing becomes a strategic advantage—providing data that leads to better product decisions and a more sustainable customer lifecycle. At V For Vibes we approach emotional response as a critical part of product performance. Emotional safety is a measurable outcome, and it should be treated with the same rigor as any physical feature. #SexTech #VForVibes #EmotionalSafety #ProductTesting #WellnessTech #Neuroscience #UserExperience

I wish I had data like this when I was advocating for a more effective ad placement strategy at Warner. For years, advertising has relied on reach and demographics to derive value. But what if engagement intensity—the emotional highs and lows viewers experience—was the real driver of ad impact? Essentially an Emotional Impact Score. The team at Mediaprobe measures that exact thing. Let me get a little technical… 🙂 They measure emotional engagement using Galvanic Skin Response (it’s the approach used in lie detector tests). With Tubi garnering an impressive 13.6 million viewers for this year’s Super Bowl, I wanted to get a sense of how consumers reacted to live sports on streaming vs. linear. Is there a difference? My gut told me that streaming would garner lower emotional scores because, let’s face it, it doesn’t always work… Analysis of over 250 million data points shows that live sports on streaming platforms generate 9% higher emotional impact than on linear TV. That doesn’t seem like a lot on the surface, but it is and the mere fact that it’s higher is even more insightful because higher emotional response leads to higher recall.  It gets better - Live sports on streaming creates more emotional peaks—the moments that make viewers lean in, remember brands, and take action. Peaks range from Level 1 (extreme, rare emotional highs) to Level 4 (more frequent, moderate reactions). And compared to linear TV, streaming delivers: - 3.86x more Level 1 (highest intensity) peaks - 2.70x more Level 2 peaks - 2.23x more Level 3 peaks - Even Level 4 peaks occur 1.82x more often So, is this why streamers are paying a premium for sports rights? More importantly, does it mean they can justify an even greater premium for rights, for CPMs? Does this change how they approach sponsorship sales? Streaming platforms are quickly becoming the home to the one thing that keeps the Pay TV value proposition in tact - sports. This analysis implies they aren't done creating value.

𝗘𝗺𝗽𝗮𝘁𝗵𝗲𝘁𝗶𝗰 𝗰𝗼𝗻𝘃𝗲𝗿𝘀𝗮𝘁𝗶𝗼𝗻𝗮𝗹 𝗿𝗲𝗰𝗼𝗺𝗺𝗲𝗻𝗱𝗲𝗿 𝘀𝘆𝘀𝘁𝗲𝗺𝘀 enhance traditional recommendation algorithms by integrating users’ emotions. While typical systems rely on user ratings to gauge satisfaction, they often miss the reasons behind these feelings. Emotions, which include a variety of feelings like excitement or frustration, offer deeper insights into user experiences. By combining ratings and emotions, recommender systems can develop richer user profiles and provide more personalized, context-aware recommendations based on both past ratings and current emotional states. 𝗜𝗻 𝗲-𝗰𝗼𝗺𝗺𝗲𝗿𝗰𝗲, if a user rates a drama movie 4/5 but feels emotionally drained, future recommendations might include uplifting dramas to balance their experience. Similarly, if a book is rated 3/5 for being too intense, the system might suggest less intense thrillers based on both the rating and emotional feedback. 𝗜𝗻 𝗵𝗲𝗮𝗹𝘁𝗵𝗰𝗮𝗿𝗲, a patient rating a physical therapy session 4/5 but expressing frustration about slow progress might receive motivational messages and suggestions for additional supportive therapies. If a high-intensity workout is rated 5/5 but leaves the user exhausted, the system could recommend a mix of high-intensity and recovery workouts to balance effectiveness. At the recent 𝗔𝗖𝗠 𝗥𝗲𝗰𝗼𝗺𝗺𝗲𝗻𝗱𝗲𝗿 𝗦𝘆𝘀𝘁𝗲𝗺𝘀 𝗖𝗼𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲 (𝗥𝗲𝗰𝗦𝘆𝘀 𝟮𝟬𝟮𝟰), the paper 𝗧𝗼𝘄𝗮𝗿𝗱𝘀 𝗘𝗺𝗽𝗮𝘁𝗵𝗲𝘁𝗶𝗰 𝗖𝗼𝗻𝘃𝗲𝗿𝘀𝗮𝘁𝗶𝗼𝗻𝗮𝗹 𝗥𝗲𝗰𝗼𝗺𝗺𝗲𝗻𝗱𝗲𝗿 𝗦𝘆𝘀𝘁𝗲𝗺𝘀 (which won the best paper award) described an innovative framework called the 𝗘𝗺𝗽𝗮𝘁𝗵𝗲𝘁𝗶𝗰 𝗖𝗼𝗻𝘃𝗲𝗿𝘀𝗮𝘁𝗶𝗼𝗻𝗮𝗹 𝗥𝗲𝗰𝗼𝗺𝗺𝗲𝗻𝗱𝗲𝗿 (𝗘𝗖𝗥) which enhances traditional conversational recommender systems by incorporating empathy. The approach enhances the ReDial recommendations dialogue data set by leveraging GPT-3.5-Turbo to annotate user emotions. It also uses reviews from external resources to create a set of responses. The two key components of ECR are: 𝗘𝗺𝗼𝘁𝗶𝗼𝗻-𝗮𝘄𝗮𝗿𝗲 𝗶𝘁𝗲𝗺 𝗿𝗲𝗰𝗼𝗺𝗺𝗲𝗻𝗱𝗮𝘁𝗶𝗼𝗻: the system maps emotions to entities (e.g., books, movies). Multi-task learning is used to learn user preferences and emotional contexts to create a more holistic user profile. 𝗘𝗺𝗼𝘁𝗶𝗼𝗻-𝗮𝗹𝗶𝗴𝗻𝗲𝗱 𝗿𝗲𝘀𝗽𝗼𝗻𝘀𝗲 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻: the system uses retrieval-augmented prompts to fine-tune pretrained models such as DialoGPT and Llama-2-Chat to retrieve relevant emotional content from the responses database for response generation. It also has user feedback integration to prompt users for explicit feedback when emotions are unclear. ECR also introduces several novel metrics such as Emotion Matching Score (EMS) and Emotion Transition Score (ETS) to measure how well the systems responses align with the users emotions and the ability of the system to positively influence the users emotional state through its recommendations. Paper: https://lnkd.in/ePEbppvY

She sent 3 people on stress leave. Then discovered this missing piece: I once coached a Fortune 500 director—let’s call her Cynthia. Three people had taken stress leave under her leadership. She had a temper. She snapped in meetings. People walked on eggshells. She was passed over for promotion twice… But she wasn’t cruel. She just didn’t know how to name what she was feeling, let alone manage it. She had no internal warning system. Frustration would spike before she could see it coming. So we started simple: ☑️ 3 emotional check-ins a day ☑️ Noticing tension in her body ☑️ Identifying emotions with precision Within months, the difference was night and day. 👉 No more stress leaves. 👉 No more explosions. 👉 Her VP nominated her for a promotion. 😉 A team that finally felt safe, and a leader who finally felt in control. If you want to build self-awareness, start here: Mindfulness meditation – Sit quietly for 5–10 minutes and observe your thoughts without judgment. This builds the habit of noticing before reacting. Journaling – Write about what happened, how you felt, and why. Over time, you’ll start to spot emotional patterns and triggers. Body scanning – Close your eyes and slowly notice sensations from head to toe. Tension, tightness, or ease often signal emotional states. Asking deeper questions – Go beyond “How am I?” to “What values are at play here?” or “Why did that reaction feel so strong?” Seeking feedback – Ask people you trust, “How do you experience me in stressful situations?” External insights expose blind spots. Tracking habits – Pay attention to default behaviors (e.g., interrupting, overcommitting) and ask, “Is this serving me—or protecting me?” Emotional labeling – Practice naming your emotions specifically: not just “bad,” but “irritated,” “embarrassed,” or “anxious.” Reflection rituals – Build check-ins into your day: before meetings, after difficult conversations, during commutes. Awareness grows through repetition. You can’t change what you can’t see. Follow me for more tools like this. And grab my 5-minute “Missing Leadership Link” newsletter from my profile. #Selfawareness #leadership #emotionalintelligence

🚀 Introducing Multi-Modal Emotion-Aware AI Agents in Healthcare 🧠 Unlike traditional chatbots or scripted virtual assistants, these AI agents synthesize signals across multiple channels—voice tone, facial expressions, biometric data (like EEG or heart rate), language patterns, and behavior—to understand how a person feels, not just what they say. This emotional intelligence enables them to interact with patients more naturally, empathetically, and effectively. 💡 Where are they making a difference? • Mental Health & Digital Therapeutics: Supporting patients through CBT, trauma recovery, or anxiety management with emotionally adaptive dialogue. • Decentralized Clinical Trials: Ensuring consent comprehension, real-time symptom tracking, and emotionally-informed protocol engagement. • Remote Patient Monitoring: Detecting early signs of distress, disengagement, or health deterioration in chronic care. • Patient Intake & Triage: Recognizing emotional cues like stress or confusion to guide better clinician interactions. • Pediatrics & Elder Care: Responding to non-verbal distress where verbal communication may be limited. • Workplace Wellness & Resilience: Enhancing cognitive performance and emotional regulation in high-stakes professional settings. • Population Health & Digital Twins: Linking emotional states and behavioral patterns with disease trajectories for public health insight. 🌐 The future of healthcare will be intelligent, yes—but also emotionally attuned. #AIinHealthcare #AIAgents #EmotionAwareAI #MultimodalAI #DigitalHealth #MentalHealth #ClinicalTrials #PatientEngagement