Decoding Happiness: An AI-driven Experiment of Self-Discovery
Decoding Happiness: An AI-driven Experiment of Self-Discovery
From Privacy-Focused Diary Analysis to Personalized Chatbot Coaching
The highlights:
I used a local AI model to analyze my diary and gain deeper insight into myself.
A chatbot personalized with knowledge about my psyche helped me reflect on my year and set new goals.
AI-driven self-analysis could aid in personal growth and play a role in mental health care.
Read time: 9 minutes.
Welcome to this new edition of Transforming Med.Tech, the newsletter in which I try to understand how disruptive innovations will transform medical technology. In this edition, I’m diving into using chatbots to analyze my diary and gain a deeper understanding of myself - it’s a longer read than usual, but I promise you it’s worth it!
After the busy work weeks of December, I cherish the first days of January as a time for reflection and planning. It’s a ritual where I delve into my professional and private life, reassessing past achievements and setbacks, and setting objectives for the future. This year, I decided to add a novel twist to this tradition by experimenting with generative AI, aiming to utilize a local Large Language Model (LLM) to analyze my diaries.
A privacy-friendly deep-dive into my diary
For the past year, I’ve been keeping a diary and enjoying writing about my adventures, small and big. Due to privacy concerns, I was hesitant to use cloud-based solutions to analyze such a personal document. Luckily, small open-source models can run on your computer with the appropriate (free) software. I asked one such model about a diary entry. Though somewhat slow, this yielded fascinating results, including a daily ‘happiness score’ and key themes influencing my mood.
To streamline the process, I wrote a Python script that automatically fed my diary entries to the LLM, extracting various metrics like family time and work-related business. The local LLM ensured my data remained offline and secure.
I observed an interesting pattern in my happiness scores over time. Generally, my happiness level hovered around a stable 8 out of 10, indicating a baseline of contentment. However, the data also highlighted certain instances where my happiness levels noticeably deviated from this average. These moments correlated with significant events – a dip in happiness aligned with a period of illness, while a sustained peak coincided with the joyful occasion that my child started to sleep through the night. Additionally, I noticed a tendency for my happiness to return to its baseline over time, a phenomenon termed the ‘blue dot effect,’ where the impact of both positive and negative events gradually diminishes.
I also delved into the statistical correlations between happiness and other metrics extracted from my diary. The results were a mixed bag – many of these correlations were insignificant and, frankly, I approached them with a healthy dose of skepticism. However, there was one correlation that was significant and seemed to ring true to my instincts: the link between happiness and family time:
A bot’s psychological analysis
The initial results from the local-LLM analysis were intriguing. They suggested that natural language processing could extract meaningful patterns from my diaries in a secure, private environment. I then took the less sensitive output – keywords related to happiness and unhappiness – and fed them to ChatGPT4 for further analysis in the cloud. I asked it to analyze the main themes of happiness and unhappiness throughout my year from this long list of (sometimes recurring) keywords. The AI’s ability to discern and rank these themes was quite accurate. Although some themes are valid for almost anybody, many resonated with my personal experiences, such as my love for my direct family and for outdoor activities:
Based on your extensive list of "happy" keywords, several key themes emerge that contribute to your happiness:
- Family and Relationships: Frequent mentions of family members, particularly (redacted: name of kid), (redacted: name of wife), and other relatives, highlight the importance of family in your life. Spending quality time with them, celebrating events like birthdays, and enjoying simple moments together are recurring themes.
- Outdoor and Nature Activities: You frequently mention activities like swimming, walking, beach visits, nature walks, and biking. This suggests a strong appreciation for the outdoors and a connection with nature.
(... the list continues and includes 10 themes ...)Further analysis also highlighted some unhappiness factors that made sense, some of which I hadn’t realized consciously yet. I then asked it to do a full psychological analysis through a Big Five personality assessment. This was insightful, but due to its personal nature, I prefer to keep the details private, though I can share an intriguing graph it produced:
Curious to enhance my well-being, I prompted the AI for suggestions to boost my happiness. The recommendations it provided were thoughtful and practical. While I acknowledge that these AI-generated suggestions don’t equate to the nuanced advice a healthcare professional might offer, having such an accessible digital coach may be of tremendous potential value. Further exploration of digital tools in psychology and psychiatry could be invaluable, particularly in areas where access to healthcare professionals or personal coaches is limited or non-existent.
An on-demand personal coach
Impressed by the depth of insights gleaned so far, I decided to take the experiment a step further, beyond yearly reflection and towards daily guidance. I developed a personalized chatbot to act as my coach, tailored to my individual needs and peculiarities. Into its ‘knowledge base,’ I integrated the other bot’s psychological analysis, a personal manifesto, my goals and ambitions, and several self-help books I frequently consult (Rick Pastoor’s GRIP is a favorite!).
Interacting with this chatbot about the past year and planning for the future proved to be quite practical. The bot was particularly helpful when it highlighted a conflict between my professional and personal objectives. Unconsciously, I had realized that this tension was there, but having this bot mention this so explicitly (and suggest concrete mitigations) was insightful.
The bot then applied a motivational interviewing style to help me better understand and tackle these issues.
Implications for personal development and healthcare
The prospect of having real-time coaching based on private AI analyses is intriguing. Privacy is key, but local AI is becoming more capable, and hardware is increasingly available (e.g., in AI-ready smartphones). Such personalized coaches could help in setting balanced long-term goals while also managing daily tasks.
The potential application of this kind of psycho-analysis and coaching extends beyond enhancing personal performance. Perhaps healthcare professionals could adopt these privacy-conscious tools as supplementary aids in therapies for burnout or mental illness. Diary analysis or daily bot interactions could offer both patients and mental health specialists a novel way to uncover and reflect upon underlying patterns and personality traits. However, it’s essential to acknowledge that implementing these tools in a clinical setting would require careful development, thorough validation, and rigorous attention to safety protocols.
Reflecting on my essence
In a creative twist, I asked my personal bot to generate an image that encapsulates my essence. The result was surprisingly touching, highlighting key elements of my identity, and symbolically represented the journey I had undertaken.
Here's an image that captures the essence of your personality and the elements that are important to you. It portrays a serene and joyful family moment in a beautiful outdoor setting, with subtle symbols of technological innovation and scientific research in the background. This image reflects the balance in your personal and professional life, your connection with nature, and your strong family bonds.
This experiment has been a revealing exploration into the capabilities of generative AI for personal reflection and goal setting. I am curious about other potential applications of this technology and its role in professional growth and healthcare. I’d love to hear your thoughts on where this technology could make a real impact.
The Jupyter notebook for running your own local analyses can be found here. Have fun!