The question-rate finding is the most interesting bit. Also the most platform-confounded. When my closest friends moved to voice and video the text question rate dropped to zero, but the underlying asking didnt. So part of the advice-friend signature is really a who-still-types-with-you signature. The author probably has the data to test that but the post doesnt say.
NDlurker 3 hours ago [-]
I wanted to do this so bad back in like 2009. I archived MSN messenger chats and my texts and everything and I figured sometime in the future I'd be able to analyze them and maybe even train a chat bot to imitate me. But over the years I lost hard drives and cell phones and accidentally deleted stuff and yeah it didn't happen. Very cool this guy was able to do it
Nition 2 hours ago [-]
I used to have saving turned on for my MSN Messenger chats back around 2001-2004. I didn't lose them. 10-15 years later or so I had a look through them and the cringe was so powerful that I deleted them all anyway.
johntash 2 hours ago [-]
Sometimes I feel bad that I lost years of chat history from then too, but you made me realize that might be a good thing.
hackboyfly 54 minutes ago [-]
This made me laugh out loud.
freehorse 51 minutes ago [-]
I have my msn logs along with a lot of old stuff in an ecrypted hard drive with a password I have forgotten. I am waiting for divine enlightment to remember the password, or quantum computers to finally come.
Weirdly glad to hear I am not the only one effectively having lost them.
marak830 43 minutes ago [-]
Well if it's bitlocker encrypted I have some good news (potentially) Yellowkey (CVE-2026-45585) is able to bypass it.
Topgamer7 2 hours ago [-]
I envy you that you manage to keep meaningful contact with dozens to hundreds of people.
1 hours ago [-]
sixhobbits 39 minutes ago [-]
I do some similar charting etc with telegram data dumps that you can still get from the "telegram lite" desktop app even though they removed the export functionality from the main app.
For removing noise you might want to look into TF-IDF instead of the manual method described in the post that I didn't understand. It basically looks for words common across the whole corpus as noise or ones that appear within a specific chat much higher than the whole dataset as interesting.
You can also do some fun stuff by finding phrases used asymmetrically eg more by one person in the convo than the other, or over time.
Wordclouds per person are also fun!
gobdovan 43 minutes ago [-]
Finally, a good use for LLMs. I would be so embarrassed to read old messages, yet LLMs just psychopatically chug along without flinching or cringing.
dwedge 1 hours ago [-]
Damn this is a nice reminder that even private chats I sent to someone else 10 years ago aren't safe from being harvested by AI
Cider9986 3 hours ago [-]
I mostly text on Signal with disappearing messages so I wouldn't be able to do this. Most people are fine with disappearing messages at 4 weeks, but a few people like to keep their chats forever.
saligne 2 hours ago [-]
there's a tool for extracting chat history from signal desktop, you could build a plaintext and attachment archive with that if it runs regularly on your pc and appends new chats from the last run.
dwedge 1 hours ago [-]
I'd be pretty angry if I found out someone I chatted to on Signal was running a service to workaround my message expiry choice and archive my messages. And breaking that trust just to run it through an LLM?
Squeeeez 33 minutes ago [-]
They might not be doing it on purpose, remember that microsoft windows "take a screenshot every few seconds and send it to an llm" thing?
rablackburn 27 minutes ago [-]
Everything old is new again. This is basically the debate over IRC Bouncers all over again.
nanocat 57 minutes ago [-]
fucken yep. don’t do this.
valzevul 3 hours ago [-]
Do you keep separate notes for things like recommendations or addresses? I often dig through my chats to find them.
Cider9986 3 hours ago [-]
Yeah I use NotesNook for big notes or projects.
I also use the Note to Self which is built into Signal and appears just like any other conversation. I use that for temporary stuff like addresses and keep it clean.
ashm1104 52 minutes ago [-]
I do wanna do the same, but at times I fear about getting too aware from the insights of the analysis, I fear my opinions my faith might change in certain people.
AdrianB1 28 minutes ago [-]
I don't understand how some people write hundreds of text/chat messages per day. I am communicating by talking to people almost 100% of non-work, most of the discussions are face to face, I write or receive a handful of texts or chats per week, maybe a dozen per month.
I find text messages impersonal and it also takes longer to communicate clearly what we need. There is so much lost. Even chats and emails for work are at risk of creating misunderstanding, especially because English is not the native language of most of my coworkers, all these adds to result in pretty low quality communication.
danielpardo 1 hours ago [-]
I would like to do something similar, but I lost a lot of whatsapp historical chats switching phones...
Don't think there is a way to recover that.. right?
dwedge 1 hours ago [-]
If you configured e2e encryption beforehand and know the key, you might get lucky with the backup files on your old phone
defenestrated 1 hours ago [-]
Do you still have those phones/Android files?
Rendered at 08:17:07 GMT+0000 (Coordinated Universal Time) with Vercel.
Weirdly glad to hear I am not the only one effectively having lost them.
For removing noise you might want to look into TF-IDF instead of the manual method described in the post that I didn't understand. It basically looks for words common across the whole corpus as noise or ones that appear within a specific chat much higher than the whole dataset as interesting.
You can also do some fun stuff by finding phrases used asymmetrically eg more by one person in the convo than the other, or over time.
Wordclouds per person are also fun!
I also use the Note to Self which is built into Signal and appears just like any other conversation. I use that for temporary stuff like addresses and keep it clean.
I find text messages impersonal and it also takes longer to communicate clearly what we need. There is so much lost. Even chats and emails for work are at risk of creating misunderstanding, especially because English is not the native language of most of my coworkers, all these adds to result in pretty low quality communication.
Don't think there is a way to recover that.. right?