Beyond the Scroll: How Social Media Algorithms Shape Your Reality

that your social media feed could know you too nicely.

While you browse social media, you discover a really typical conduct: you watch one video, and all of the sudden your timeline is flooded with extra of the identical. 5 years in the past, it felt a bit like magic. However in the present day, we speak about “the algorithm” as if it have been a mysterious entity pulling strings in some Silicon Valley basement. The reality is way much less dramatic, and way more fascinating.

The algorithm isn’t inherently evil, it doesn’t sit there plotting your radicalisation. It’s only a chunk of code working cosine similarities and weighted averages, making an attempt to foretell what you’ll click on on subsequent. The difficulty is what we work together with creates engagement. And the surest approach to hold people engaged seems to be the worst approach to hold them knowledgeable (rage-baits, faux information, or worse).

This publish is about how suggestion engines work, why they tilt us towards echo chambers, and, as a result of studying a few factor isn’t the identical as seeing it, we’ll construct one from scratch, level it at actual information information, and watch the bubble kind.

The Engagement Engine: How Recommenders Work

A social media algorithm is, at its coronary heart, a curator. Its job is to sift via thousands and thousands of posts and serve you those you’re more than likely to interact with: click on, watch, like, share, rage-comment on. It does this primarily based on one phrase: information.

Each motion you’re taking is a clue:

• Which posts you linger on (even with out clicking)
• Which movies you watch, and for the way lengthy
• Which accounts you observe, mute, or block
• Which matters you seek for at 1 a.m.

Utilizing machine studying, the algorithm spots patterns on this firehose of behaviour. It’s always asking the identical query: what retains this particular person on the platform longer? Do not forget that that is the biggest objective of any social media firm: conserving you on the platform longer.

Two basic strategies sit beneath most recommender methods:

• Collaborative filtering finds customers who behave such as you and recommends what they appreciated. If Alice and Bob each beloved The Matrix and Inception, and Alice additionally beloved Interstellar, the system nudges Interstellar to Bob. Fairly simple to grasp.
• Content material-based filtering seems on the traits of what you’ve appreciated and finds related issues. In case you watch a number of cooking movies, it surfaces extra movies tagged “cooking”, “recipe”, or “knife abilities”, they resemble what you already loved.

Actual platforms mix these strategies with tons of of different alerts. However the core thought is similar: be taught out of your behaviour, predict what else would possibly seize you.

The algorithm doesn’t intend to point out you unhealthy or false content material. It optimises for engagement. And one of many surest methods to maintain people engaged is to faucet into our feelings, especially the strong, negative ones. Or movies of cats.

Constructing a Information Recommender on Actual Knowledge

Let’s cease speaking about this abstractly and construct one. We’ll use actual anonymised click on logs from Microsoft News. The dataset is known as MIND (Microsoft Information Dataset), printed for educational analysis by Microsoft Analysis. This pattern accommodates 50,000 customers, over 51,000 English information articles throughout 17 classes (information, sports activities, finance, life-style, well being, journey, and extra), and 156,000+ actual impression classes, every recording what a person was proven and what they clicked on. The entire thing matches in about 30 traces of Python, though you don’t really want to now this inde element:

import numpy as np
import pandas as pd
from scipy.sparse import csr_matrix
from sklearn.metrics.pairwise import cosine_similarity

# Construct a sparse person × article matrix (1 = clicked, 0 = did not)
matrix = csr_matrix((np.ones(len(clicks)), (user_rows, article_cols)),
                    form=(n_users, n_articles))
def suggest(user_id, matrix, top_n=15, n_neighbors=50):
    """Discover 50 most related customers and rank the articles
    they clicked that our person hasn't seen but."""
    u = user_idx[user_id]
    
    # Cosine similarity between this person and everybody else
    sims = cosine_similarity(matrix[u], matrix).flatten()
    sims[u] = 0  # do not suggest to your self
    
    # Take the highest 50 most related customers
    top_neighbors = np.argsort(sims)[-n_neighbors:][::-1]
    weights = sims[top_neighbors]
    
    # Rating articles by weighted sum of neighbour clicks
    scores = np.asarray(matrix[top_neighbors].T.dot(weights)).flatten()
    
    # Zero out articles the person already clicked
    scores[matrix[u].toarray().flatten() > 0] = 0
    
    # Return the top-scoring articles
    top_articles = np.argsort(scores)[-top_n:][::-1]
    return top_articles

Cosine similarity finds your fifty closest neighbours, individuals who click on on the identical sorts of articles you do. We take the articles they clicked, weight them by how related every neighbour is to you, and serve the highest fifteen. That is the base of what powers a billion-dollar trade.

Coswhat similarity?

Cosine similarity would possibly sound like one thing out of a math textbook, however bear with me, it’s simpler than it seems. To indicate you the way it works, let’s take a fast detour.

Think about the next information factors scattered throughout two axes, mechanical vs. organic, and cuteness:

Cosine similarity measures the angle between two arrows, every one ranging from the origin (0,0) and pointing towards one among our information factors. The smaller the angle between them, the extra related the 2 gadgets are.

Consider it this fashion: if two arrows are virtually pointing in the identical course, the gadgets they signify share related traits. Take cats and canine for example. Each rating excessive on ‘organic’ and excessive on ‘cuteness’, so their arrows level in almost the identical course and cosine similarity returns a worth near 1 (its most).

But when we examine cats with teddy bears, though they’re related on the lovable dimension, they’re completely different on the organic axis:

If we examine cats with teddy bears, though they’re related on the lovable dimension, they’re completely different on the organic axis, a cat is absolutely organic, whereas a teddy bear scores zero.

This pulls their arrows aside.The angle between them widens, and cosine similarity returns a decrease worth, reflecting that regardless of sharing one trait, these two objects occupy very completely different areas of our area.

And, in fact, evaluating cats to vehicles, give virtually no similarity because the arrows between each level in several instructions:

AI fashions use this sort of data to suggest content material that’s more likely to set off an identical response in you. Think about a two-dimensional area the place one axis captures how a video makes you’re feeling (calm, entertained, outraged) and the opposite captures its subject. Each video will get plotted someplace in that area.

In case you click on on a political video that makes you indignant, and also you watch it all over. The platform registers each dimensions: the subject and the emotional response. Utilizing cosine similarity, it finds different movies whose ‘arrow’ factors in the identical course (rage-baiting political movies) and serves them to you subsequent. The extra you interact, the extra confidently the algorithm learns which nook of that area retains you watching.

Meet Person U92876 (let’s name it Joe): The Sports activities Fan

I picked a person from the MIND dataset whose studying historical past is pure sports activities, NFL energy rankings, NBA commerce rumours, MLB bans. It learn twenty-five articles, all sport.

Let’s ask the recommender what to serve them:

The class breakdown:

• 40% sports activities
• 13% information
• 13% autos
• 34% scattering of every little thing else.

The algorithm recognises this particular person’s sports activities behavior and feeds it again, but it surely additionally serves a fairly assorted weight loss program. There’s politics, leisure, life-style, finance. Not unhealthy, proper?
Now watch what occurs.

The Second of Curiosity

I simulated one thing way more frequent than an enormous rabbit-hole binge: a second of idle curiosity.

Our sports activities fan didn’t spend hours studying politics. their preliminary feed, they merely clicked on three gadgets that caught their eye:

• The information story about Joe Biden.
• The information story about Mitch McConnell.
• The video about Trump’s assaults.

Simply three clicks in lower than ten minutes of studying and watching. Three tiny breadcrumbs left for the algorithm and Joe goes on along with his life throughout the remainder of the day.

Now, if we ran these clicks via the essential 30 traces of Python code we wrote earlier, nothing a lot would occur. Mathematically, 25 historic sports activities clicks would nonetheless overpower 3 new political clicks. The algorithm would nonetheless see a person who’s 89% excited by sports activities, and the feed would barely budge.

However right here is the crucial secret sauce of contemporary social media: Recency Weighting (or Time Decay).

Actual algorithms don’t deal with all of your clicks equally as a click on you made three years in the past is virtually historic historical past; a click on you made three minutes in the past is gold. To maintain you hooked within the present session, platforms apply a heavy multiplier to no matter you might be doing just lately.

A single line of code implements this within the algorithm we noticed earlier. If we determine that the newest clicks ought to carry as much as 100 occasions extra weight than older ones, we may write one thing like this:

time_decay_weights = np.array([0.1 if historical_click else 10.0 for click in user_history])

If we do that, let’s run the suggestions once more:

Right here’s the harm that simply 3 clicks have completed to our Time Weighting suggestion system:

Political information went from 13% to 40% of the feed. A 3x improve. From one night of clicking and studying three items of reports. Sports activities (the factor this particular person has learn for years) can drop from the dominant class to second place. The algorithm didn’t pause to assume “maintain on, this particular person has 25 sports activities articles of their historical past, and one night of politics doesn’t outline them.”

It doesn’t assume, it simply recalculates time weighted similarity matrices, discovered a brand new set of neighbours and served what different customers that clicked on this will likely take pleasure in.

Two issues bounce out:

• The pace. It could take one night to flip a person’s total feed composition. Actual platforms recalculate quicker than this demo as they replace in actual time. You in all probability discover this in your feed with adverts associated to merchandise you’ve been looking these days.
• What disappears. This isn’t nearly what the algorithm provides, however additionally about what it removes. The person’s informational weight loss program didn’t simply get extra political, it bought narrower. And narrower is the actual hazard right here

Notice: actual platforms don’t publish their decay constants, so that is illustrative, not a measurement, however the mechanism is actual and the course is what issues. My 100x instance is probably an exaggeration of the recency bias.

What analysis tells us

You now understand how clicks affect what the maths of what the algorithm reveals you subsequent.

However this will get worse — content material that makes us indignant, fearful, or shocked glues us to the display much better than content material that makes us really feel good or knowledgeable. Social media firms didn’t engineer this consciously, their algorithms merely found it.

A massive 2025 study analyzing the digital trace data of 25,000 SmartNews users found that humans possess a trait-level “negativity bias” when choosing information. Evolutionarily, we’re hardwired to concentrate to threats, avoiding hazard was crucial to our ancestors’ survival. What occurs when this historic intuition meets trendy machine studying? The research confirmed that personalised suggestion feeds take our inherent negativity bias and actively increase it.

Moreover, data from researchers analyzing hundreds of millions of posts on platforms like Fb and X (previously Twitter) reveals that social media customers are roughly 1.91 occasions extra probably to share detrimental information hyperlinks than optimistic ones. Negativity equals virality, and the outrage loop is born.

The Cognitive Toll: It’s Not Simply What You Suppose, It’s How You Suppose

The affect of those algorithmic loops isn’t nearly the kind of content material we devour; it’s about the way it basically alters our brains. A recent 2025 systematic review analyzing 71 research and 98,299 individuals of short-form video feeds (like TikTok, Instagram Reels, and YouTube Shorts) discovered profound cognitive penalties.
Elevated engagement with these endless-scroll platforms is related to poorer cognitive efficiency, particularly impacting our sustained consideration and inhibitory management.

Psychologists level to a twin technique of habituation and sensitization to clarify this phenomenon. The speedy, high-stimulation nature of brief movies desensitizes us to slower, extra effortful duties like studying a e book or deep problem-solving. On the similar time, the algorithm’s instantaneous supply of curated content material sensitizes our mind’s reward system, reinforcing impulsive engagement patterns and encouraging the routine looking for of instantaneous gratification.

Heavy customers of those platforms exhibit lowered electrophysiological exercise throughout attention-demanding duties. Some researchers even level to structural variations in key cognitive management areas, together with the prefrontal cortex and striatal reward circuits, linked to this fixed bombardment of extremely rewarding algorithmic stimuli.

The Societal Price

As a result of mathematical matrices, every of us in our personal personalised bubble of data.

Within the brief time period, it’s annoying for most individuals. However zoom out and the image darkens. When algorithms feed us content material that confirms what we already imagine, we expertise affirmation bias on steroids.

These filter bubbles deepen the social divide now we have in the present day. We’ll proceed to be extraordinarily divided and there’s no finish in sight for this chasm.

Misinformation thrives in closed loops as a result of false tales don’t get uncovered to scrutiny outdoors the bubble. By the point a fact-check goes out, the unique lie has completed a lap across the platform and constructed a small military of believers.

And democracy, which is determined by a shared baseline of actuality and a few willingness to argue in public, takes successful when residents occupy completely completely different actuality bubbles.

Reclaiming Your Feed

You’re not powerless right here. The algorithm is responsive however there a few issues you are able to do, that, though annoying, could take you out of your bubble.

The identical mechanism that constructed your bubble can be utilized to widen it. Some sensible transfer:

• Diversify the inputs. Actively observe a couple of sources outdoors your consolation zone. In case you lean a technique politically, observe some considerate voices from the opposite aspect.
• Reset periodically. Clear your watch historical past. Use “Not ” on ideas that hold haunting you. Strive the platform logged out, or in incognito, and see how completely different the world seems with out your information.
• Use chronological feeds. Most platforms nonetheless allow you to swap off the algorithmic rating and simply see posts from individuals you observe, so as.
• Pause earlier than sharing. Each like, remark, and share is a vote for “extra of this, please.” If one thing makes you livid, that’s precisely when the algorithm is more than likely to be exploiting you.
• Restrict the time. Set screen-time limits. Schedule offline hours. The much less you rely on the feed in your data weight loss program, the much less energy it has to form what you imagine.

Past the Bubble

I hope this weblog publish knowledgeable you on how these suggestion methods bubbles work. We constructed a recommender on actual information information, and it took three clicks to flip a sports activities fan’s feed from 40% sports activities to 53% politics.

Step one to breaking free is just being conscious. Subsequent time you end up in a web based frenzy, take a breath and ask: Why am I seeing this? Who advantages from me reacting this fashion? The reply normally traces again to an algorithm doing its job, and that job isn’t “informing you.”

Keep knowledgeable, keep open-minded,
— Ivo