Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How Cambridge Analytica’s Facebook targeting model really worked

niemanlab.org

Post reply on HN
Print view View original

31–40 of 210 posts

Re: How Cambridge Analytica’s Facebook targeting model really worked

#31

Post by alexbeloi »

daenz wrote: post #3

Am I understanding this correctly? Facebook user data (likes/profile info) was scraped to produce low-dimension feature vectors for users (similar to word2vec). These feature vectors were then run through some ML model to predict...what exactly? Targetability for effective political ads?

They used it to predict political affiliation of people that don't explicitly state a party preference.

The two parties already have a list of registered party members (and they can see who on Facebook explicitly states their party preference), for those members the main goal is higher turnout (they are the training data). The other voters they're interested in are unregistered (e.g. independent) voters that are likely to be on their side ideologically.

The core idea is very simple, they believe that if someone says they're independent, but their preferences/features (age, gender, location, likes, posts) are predicting moderate or high likelihood of $PARTY affiliation, then showing this person political ads may move them from 'maybe vote for $PARTY' category and get them in the 'definitely vote for $PARTY' category.

If you have continuous access to new Facebook data as you're serving ads, you can verify your ads are working on an individual basis by checking the predicted 'score' for $PARTY affiliation predicted by your model before and after an ad (I want to stress that this can be done on an _individual basis_). The likely sequence of events is that they did AB testing on different kinds of ads and found that fake inflammatory ads were most effective at achieving this goal in a very measurable way ($PARTY score), the resulting media/political atmosphere is collateral damage (hopefully unintended).

Source: I am a data scientist / machine learning scientist and this is how I would do it and how it seems to me others. I don't work on political data but I have worked on personalized recommendations which are similar.

Re: How Cambridge Analytica’s Facebook targeting model really worked

#33

Post by emodendroket »

jacquesm wrote: post #29
emodendroket wrote: post #20

Earlier quoted context omitted.

It seems like the purpose was narrowly tailoring messages, which is something political campaigns are really keen to do now (Obama's campaign was kind of a trailblazer here, right?).

> Obama's campaign was kind of a trailblazer here, right? It's a pretty big gap between using and abusing social media and as far as I know Obama's campaign did not 'narrowly tailor messages'. They did target broad groups using generic messages and they did quite effectively use social media presence to build support. But they did not - as far as I know, so please correct me if I'm wrong - go so far as to single out…

https://devumi.com/2017/12/social-media-case-study-how-barac...

> The former president also hired Facebook co-founder Chris Hughes to help in developing his social media strategy. Obama furthered the use of Facebook for his 2012 re-election bid, utilizing it to encourage young people to cast their votes. His team developed a Facebook app that looked into supporters’ friends list to find younger voters. The team then asked supporters to share online content with these voters. More than 600,000 supporters responded to the call, sending content to over 5 million contacts.

> During his presidency, Obama continued to use Facebook to reach out to the public. In 2016, he became the first president to go live on the site, just before his final State of the Union Address.

Re: How Cambridge Analytica’s Facebook targeting model really worked

#34

Post by RpFLCL »

lordnacho wrote: post #10

Finally, I was waiting for someone to talk about the model itself. It makes sense that SVD or something like it (PCA, co-occurrence, etc) would be used. But I also wonder what exactly you are going to do with the predictions. What exactly do you show to someone to make them more likely to go and vote if they are inclined to vote your way, or make them stay at home otherwise? Is there evidence that whatever you're sho…

One example I can provide is of gun control topics.

If you understand someone's mentality on the subject you can decide if they see:

1) An ad with someone breaking into a home and the homeowner defending themselves with a firearm (sell insurance?)

2) A grandfather and grandson on a hunting trip (hunting supplies?)

3) Or maybe gun violence hotline with powerful images.

The people seeing these ads are under the assumption that everyone else sees them, not that it's specifically targeted at their personality type. These affect if you think other people understand your issue or not. Thus affecting your motivation and attitude.

If you see an ad that fits your mindset, you think you're on the majority side. This was powerful in classic media, it's just as powerful now.

Re: How Cambridge Analytica’s Facebook targeting model really worked

#35

Post by spitfire »

When talk about CA first emerged on HN before the election some posters found the original papers referred to. They were looking at pictures in the story and zoomed in to find the titles.

I cannot find those posts for the life of me again. Not suggesting anything nefarious here, I just can't find them. Does anyone have a link to those early conversations or make copies of the papers?

I made copies earlier but deleted them before I put them into my papers archive.

Re: How Cambridge Analytica’s Facebook targeting model really worked

#36

Post by dazc »

godelski wrote: post #18
rjurney wrote: post #5

Earlier quoted context omitted.

It's a hard problem but Netflix's model represents the state of the art in machine learning for recommendations. Still scared of the singularity? :)

Personally, I used to get substantially better results. It would suggest to me a movie I'd never seen before with a score above 90, I'd watch, and enjoy. Now I'm getting things like kids shows suggested to me. I double checked by history to make sure no one watched one on my account, but they keep popping up with high percentage. I also really like horror and get weird suggestions [1] for similar movies. After I watc…

Since switching from 1-5 start ratings to like or dislike it's gotten much worse.

I honestly thought the 1-5 ratings were not useful since I either like or don't like movies, I am not interested in nuances. But, it's not working out as I expected.

Re: How Cambridge Analytica’s Facebook targeting model really worked

#37

Post by jacquesm »

emodendroket wrote: post #33
jacquesm wrote: post #29

Earlier quoted context omitted.

> Obama's campaign was kind of a trailblazer here, right? It's a pretty big gap between using and abusing social media and as far as I know Obama's campaign did not 'narrowly tailor messages'. They did target broad groups using generic messages and they did quite effectively use social media presence to build support. But they did not - as far as I know, so please correct me if I'm wrong - go so far as to single out…

https://devumi.com/2017/12/social-media-case-study-how-barac... > The former president also hired Facebook co-founder Chris Hughes to help in developing his social media strategy. Obama furthered the use of Facebook for his 2012 re-election bid, utilizing it to encourage young people to cast their votes. His team developed a Facebook app that looked into supporters’ friends list to find younger voters. The team then…

Yes, that pretty much confirms what I wrote above. Your point being?

Please read the article and compare what we know about Cambridge Analytica vs what the Obama campaign did, it is comparing snipers with someone setting off fireworks.

Re: How Cambridge Analytica’s Facebook targeting model really worked

#38

Post by r00fus »

NoodleIncident wrote: post #22
lordnacho wrote: post #10

Finally, I was waiting for someone to talk about the model itself. It makes sense that SVD or something like it (PCA, co-occurrence, etc) would be used. But I also wonder what exactly you are going to do with the predictions. What exactly do you show to someone to make them more likely to go and vote if they are inclined to vote your way, or make them stay at home otherwise? Is there evidence that whatever you're sho…

Shortly after the election, I read something saying that the actual ads were targeted soundbites at specific demographics likely to vote Democrat, run shortly before the election with the intention of suppressing voter turnout.

So negative advertising aimed the core constituency of the opposition's voters speaking to their deep seated concerns about their candidate.

I could imagine this working on Dem voters who are wavering on Hillary with leads like "she thinks the TPP is the gold standard" etc.

Re: How Cambridge Analytica’s Facebook targeting model really worked

#39

Post by emodendroket »

jacquesm wrote: post #37
emodendroket wrote: post #33

Earlier quoted context omitted.

https://devumi.com/2017/12/social-media-case-study-how-barac... > The former president also hired Facebook co-founder Chris Hughes to help in developing his social media strategy. Obama furthered the use of Facebook for his 2012 re-election bid, utilizing it to encourage young people to cast their votes. His team developed a Facebook app that looked into supporters’ friends list to find younger voters. The team then…

Yes, that pretty much confirms what I wrote above. Your point being? Please read the article and compare what we know about Cambridge Analytica vs what the Obama campaign did, it is comparing snipers with someone setting off fireworks.

Look, I don't think anyone can realistically doubt that Obama's campaign was the first to effectively slice-and-dice the electorate and use social media to target them. You're arguing against a much more expansive claim than I'm making.

Re: How Cambridge Analytica’s Facebook targeting model really worked

#40

Post by ikeyany »

emodendroket wrote: post #19

I am really puzzled by the Cambridge Analytica scandal. It's not particularly savory, but is there something happening here that it wasn't basically already known about how Facebook worked? By the protests of their own executive, the system was working as designed, and at worst Cambridge Analytica misled them about how they intended to use the data, right? There was no actual security breach here, as far as I can und…

Who said anything about a security breach? Most of the controversy has been about the company influencing elections using data scraped from people (and their friends) unaware of what the data was being used for.
Post reply on HN