Chat: Is it possible for us to infer which high school they go to from geoAPI

Raw text

Transcribed text as recorded, including headers and formatting fragments.

Case 4:22-md-03047-YGR Document 2648-9 Filed 01/20/26 Page 1 of 4 AMENDED Exhibit 43 PLAINTIFFS' OMNIBUS OPPOSITION TO DEFENDANTS' MOTIONS FOR SUMMARY JUDGMENT Case No.: 4:22-md-03047-YGR MDL No. 3047 In Re: Social Media Adolescent Addiction/Personal Injury Products Liability Litigation Document 2648-9 Filed 01/20/26 Page 2 of 4 Case 4:22-md-03047-YGR Message From: Sent: [/O=THEFACEBOOK/OU=EXTERNAL (FYDIBOHF25SPDLT)/CN=RECIPIENTS/CN= 10/5/2017 12:55:16 AM To: 1; LA Subject: Message summary [{"otherUserFbId":null,"threadFbId":1319533988159383}] Attachments: sticker.png (10/04/2017 16:07:54 PDT): >hey art, the Instagram teen's team is currently doing some data analysis around local for teens. Specifically we are interested to study teen penetration and engagement on school level in US. So our question on our end is, let's say we have location collection enabled (via geoAPI) and we know someone is a teen. Is it possible for us to infer which high school they go to from geoAPI, purely for analysis purposes, so it's fine if the data is anonymous (10/04/2017 16:14:59 PDT): >you can map the location to a polygon if there as an entity for the school with a polygon associated to it (10/04/2017 16:15:26 PDT): >this is just tech feasability commentary i dont know what the privacy implications here would be on person-to-place (10/04/2017 16:16:29 PDT): >thanks.) 11 and @ thoughts? (10/04/2017 16:17:13 PDT): >do you have anyone on your team with experience around this (10/04/2017 16:17:16 PDT): >or a team we could talk to >a (10/04/2017 16:17:49 PDT): >cur tous how FB did their school level analysis (10/04/2017 16:20:51 PDT): >a good starting point can be to post on fburl.com/LOCQA this can be places data team and/or PVD i can recommend some folks to cc if you dont get a reponse on the post < (10/04/2017 16:43:07 PDT): >wants to take a lead on that? (10/04/2017 16:56:20 PDT): >Yah sure I'll take a look (10/04/2017 16:57:01 PDT): >Just clarification: so there is capability for us to match a location to school then so long as that school is an entity matched to the polygon? (10/04/2017 16:57:39 PDT): >you also have to run the analysis during school hours haha (10/04/2017 16:58:01 PDT): >otherwise the focation will update out of school (10/04/2017 17:02:44 PDT): >Want you mean the data is real time and not stored for offline purposes? (10/04/2017 17:03:34 PDT): >yup (10/04/2017 17:06:24 PDT): >Do we not store the location of teens throughout the day across multiple days? (10/04/2017 17:06:36 PDT): >nope, we get one location and then we delete it (10/04/2017 17:06:43 PDT): >when we get a new one (10/04/2017 17:07:22 PDT): HIGHLY CONFIDENTIAL (COMPETITOR) META3047MDL_RVOL003 META3047MDL-003-00022355 Case 4:22-md-03047-YGR Document 2648-9 Filed 01/20/26 Page 3 of 4 >Oh changes so basically if they open the app somewhere that is not the school most recently, then this (10/04/2017 17:07:29 PDT): >I.e. When they're at home or on weekends (10/04/2017 17:07:33 PDT): >yeah... (10/04/2017 17:08:06 PDT): >Is the reasoning for this because of privacy concerns? (10/04/2017 17:08:27 PDT): >yup, Storage costs + battery drain (10/04/2017 17:08:35 PDT): >Also they have to actually open the app AT school for us to hope to get the school location (10/04/2017 17:08:43 PDT): >that too (10/04/2017 17:10:48 PDT): >Hmh interesting, let me do some more investigation as to how fb does their school analysis to see if we can replicate something on our end with less constraints (10/04/2017 17:11:04 PDT): >they probably use their self identified school (10/04/2017 17:11:14 PDT): " >Do we hope to eventually be at a place where we might machine learn a teens important" locations? (10/04/2017 17:11:34 PDT): >Well from what I last checked that they use explicit naming of schools, but that only gets 40% of coverage (10/04/2017 17:11:49 PDT): >check out E GEDAPI (10/04/2017 17:11:49 PDT): >https://oumicern.facebook.com/intern/wiki/GeoAPI/ (10/04/2017 17:11:49 PDT): >But maybe they have other means of proxying from elsewhere? (10/04/2017 17:12:01 PDT): >maybe ke Tirescage (10/04/2017 17:12:12 PDT): >assigned school + social connections (friends of friends in that network) (10/04/2017 17:13:57 PDT): >Cool thanks Do we have the same info on IG users? Or are we hoping to map IG users to FB users to pull this location data? (10/04/2017 17:14:10 PDT): >so Us Teens aren't on FB (10/04/2017 17:14:21 PDT): >so we are hoping that the location data would enable us to build our own assignments (10/04/2017 17:14:39 PDT): >1.e. Structur my this data, since we don't have the structured data of self labeling (10/04/2017 17:14:40 PDT): >Got it - that's what I meant, so we don't have the same system built in place yet (10/04/2017 17:14:48 PDT): >yeah, not yet! (10/04/2017 17:15:44 PDT): >KK - I think this is a conversation worth having in person as well just to flush out the details of how we plan to map teens/non- FB to a location (10/04/2017 17:15:49 PDT): shared: sticker.png (10/04/2017 17:18:31 PDT): HIGHLY CONFIDENTIAL (COMPETITOR) META3047MDL_RVOL003 META3047MDL-003-00022356 Case 4:22-md-03047-YGR Document 2648-9 Filed 01/20/26 Page 4 of 4 >https://our.intern.facebook.com/intern/dex/location-data/work-school-location/?hc_location=ufi (10/04/2017 17:18:35 PDT): >might be useful (10/04/2017 17:55:16 PDT): >thanks! HIGHLY CONFIDENTIAL (COMPETITOR) META3047MDL_RVOL003 META3047MDL-003-00022357