Yes, the title of this post is an example of something like one of the many so called “Listicles” that have been littering the dev.to feed. With th...
Some comments have been hidden by the post's author - find out more
For further actions, you may consider blocking this person and/or reporting abuse
Hi.
I have to agree with you.
I've read a lot of listicles and have adopted none of the tools I saw listed.
One-liners? Some are useful, of course, but they don't make an expert out of a noob.
75 sites to help me master 39 techniques? Ain't got no time for dis! :)
I don't really know! Possible solutions:
listicletag that we can filter out from our feed?Seconding the idea of the listicle tag! And allow admins to add it after an article is published.
Thirding it? Whatever it is, I agree too!
Thanks for commenting! I think the listicle tag is a great idea!
Here's a discussion on the topic from a few days ago:
The Conundrum of the "Top X" Articles 🤔
Rafał Goławski ・ Dec 8 '23
It includes a few possible solutions, updates from DEV team, and a general comments on the issue.
Thinking about this some more, I think a "Listicle" label might help. Most authors are unlikely to use it, so it should also be possible for mods to assign it to the article, in a way that's not possible to change easily by the author.
But apart from the listicles problem, I've written how groups of people are inflating the reaction metics in the first hours of the post being published:
This is a much-needed discussion, so thanks for bringing it up - whether through an AI-assisted post or not. 😅
There have always been a lot of "Top X" articles, but I've also noticed the recent increase. What's worse, I think some are playing the DEV algorithm to their advantage.
Many of these articles have their reactions/bookmarks "maxed out", i.e. it's very visible that a few users gave all 5 reactions possible, and also bookmarked the post. On top of that, these stats grow rapidly in the first hour of the post being published. That's not a typical behavior and likely indicates a group of people trying to prop up the post (e.g. for marketing efforts). This, in turn, puts the post at the top and drives the actual engagement.
Now, asking your friends and colleagues to upvote your post isn't something bad in and of itself, but it seems to be an organized and repeated effort, that seems to feature articles of lesser and lesser quality over time.
On the other hand, I'm also not fully opposed to "Top X" articles. I found them useful many times, whether looking for a tool in a new category or doing some research.
I'm also guilty of writing a few of my own, though, in recent times, I tried to both limit it and, when writing one, focus on a few options only, in greater detail. I feel like such "Top 3s" can deliver more value and insight than "Top 50", which is not much better than a Web search.
All in all, the DEV algorithm should be changed to prevent these articles from getting to the top of the feed so often. Some possible suggestions:
If these changes work, fewer of these posts will be getting to top, there will be less incentive to write these, and there will be a greater variety of authors and topics reaching the top of the feed.
It's done primarely to listicles (low effort to write, low effort to get it to the top), but can really affect all categories, populating the top feed with low quality content. I don't have any good ideas on how to solve it though.
Don't think the initial engagement are not a bunch of alt accounts running an automated process... I think there should be an option to downvote a post (yea, I know, it's not optimal) in order to prevent these articles from reaching the top.
Downvoting brings another set of issues, but it's certainly worth considering. As for initial engagement - whether that's alt accounts, bots, or just affiliated groups (most listicles are marketing material) - the result is the same with low-quality content on top of the feed.
FWIW - Trusted Users/Mods do have the ability to downvote a post in the background with a "Low Quality" tag as well as a "High Quality" upvote.
Cool! I hope they work on the post quality!
I know, I have access to it. However, I often don't feel good marking a post "Low Quality" just because it's a listicle or it has artificially elevated reactions. I end up using the option only for the worst pieces.
This might be an issue with me, but I'd be more comfortable assigning a label/tag or in some other way, informing DEV algorithm, that the article should be (at least slightly) deprioritized.
I would say that as a moderator, you are expected to down rank junk or spam posts and promote code content. Of course, I'm not one, so… (I am one on other sites, though.)
Downvoting is possible by Mods and Trusted Users, but I find it hard to downvote real content when there is so much spam and off-topic stuff. A policy change or a view by that moderation community could have an impact, but damn, it feels like censorship rather than trying to keep the feed clean of outright scams or spam.
Yea, it does feel like censorship. Another member suggested a dedicated tag that can be added by mods and then filtered out from our feeds. This may be a less invasive approach.
Yes, that's my preferred option for sure. I've had my hard written content downvoted before and I can tell you it upset me a lot - it's why I never do it myself.
Thanks for commenting! I have seen that post, I even commented on it. :D
Depending on the appetite and compute available to solve the problem, there might be some nlp solutions to spcifically ditch out listicles. It seems reasonable that a text classifier could be run over each post and a 'listicle' value associated with the metadata.
However, some listcles are good, I've particularly enjoyed many of the articles posted by Quine recently, which are listicles, but to FOSS repos that seem to be a little sflying under the radar in a field I'm interested in.
Quine
I'm not certain of the feed algo on Dev.to, but this seems like the content type of a listcle is a symptom of the underlying issue which might be disingenuous user engagement itself? (e.g. boosting posts in a way that doesn't reflect the quality of content)
BTW, I seem to be a moderator on here (not sure how that happened tbh), and this is my notification feed a second ago:
Only one of these has anything to do with programming, and they all seem to be advertistments of some form of scam?
I agree that there are good listicles out there. However, with more of them ending up on top of the feed (especially with artificial reactions), there's less and less incentive to create good content.
I've seen recent listicles being nothing more than a bunch of links with animated cover image. Not even one paragraph of description. Essentially an equivalent of a copy-paste from Google/GitHub search, with some formatting on top.
Quine indeed has published what I think are examples of good-enough listicles, with original content, notes, etc.
Thanks Arek! It's great to hear you think we provide good content in our articles. 🙏
Hey Dave! We are super thankful for the mention here. We have some cool articles being released soon, so hopefully, you will enjoy reading them as well! 🙏
Depends on the listicle.
If it's mostly first the leading company and then only general libraries that everybody posts, yeah, it's shitty (I don't need another person to list LangChain.)
However, researching and curating an authentic list of libraries you have never heard about is a great way to learn and see new stuff.
I agree. Listicles can be good. The problem is, with more and more of those on top of the feed (likely via artificial reactions), there's less incentive to create good listicles (or any kind of content) and less room to compete for those without affiliated up-vote groups or many alt accounts.
I think it's fair to say that, in recent months, the quality has been degrading. Listicles have been abused as a blatant marketing material and growth hack, especially useful for new Dev Tools or OSS libraries. Some recent ones I've seen are just a bunch of links - no insight, original thoughts, reviews, etc. While the list might have been curated, it's the equivalent of Google/GitHub search results turned into low-effort content.
Again, I think listicles aren't the biggest problem and can be beneficial to the community. I think fewer list items and more insights for each one are the way to go, e.g. a "Top 3 best tools in a category", comparing all the listed tools in-depth (more a comparison article), or helping beginners understand which tool is recommended for which tasks.
The biggest problem is more and more people playing the relatively simple DEV algorithm to their advantage. Easy way to the top removes the incentive for quality and, in time, degrades the whole community, i.e. people don't come back because there's less and less valuable content on the site.
It tends not to agree with the algorithm part.
It's popular because it directly addresses a broad audience, mostly juniors (the main audience of DEV.)
listicles work well on Twitter and Linkedin for the same reasons.
I do agree it's mostly for marketing :)
Yeah, unfortunately I have to hard disagree. There's been a few articles - including a recent "2_ OSS libraries to launch..." (I don't want to point fingers, thus little detail) article that I've caught, basically the moment it was published.
Every reaction and bookmark was getting +1 basically on every site refresh. Even if somehow article was that popular, right away since its publication (very unlikely), everyone adding all possible reactions (+ bookmark) isn't natural.
So, I think likely alt-accounts or just a group of people. Quite hard to think of an algorithm fix for that issue. It'll likely require some mod action.
This kind of behavior is damaging for the community and authors who don't have this kind of "support group", or just want to play fair.
Either way, once the article is at the top of the feed, then the actual "marketing" happens - website visits, GitHub stars, etc.
I don't particularly like junior/senior separation (I'm a freelancer so I've never recieved my label 😅), but I think even juniors can get tired of reading the same type of content again and again. I remember starting out, I prefered reading detailed, technical artlices that actually introduced me to new tools or concepts - that's my preference to this day.
Top feed != views actually :)
You might fake the reaction and save, but it will not affect the amount of views.
It can give a push to the article.
If feed != views, then there would be no point in doing this - especially repeatedly, which currently seems to be the case. That said, even if there's really no benefit to doing this, I guess it'd only be beneficial to everyone if such behavior was prevented somehow - fair stats and views for everyone.
I know how this all sounds (I'm considering diving deeper into this in a dedicated blog post), but I think you, as an experienced Head of Growth, can agree that there's a case to be made here. :)
Thanks for your opinion!
I agree, some can be more in depth, however this is usually not the case. But, I do have to hide your comment as I am devoted to making a better internet for children, which includes counteracting content with filthy language. Thanks for posting!
Ha ha, for those reading author just made a listicle. Talks about how bad listicles are, goes on to make one.
15 Useful Bookmarklets for Web Devs (What Are They, Anyway? 🤔)
Best Codes ・ Dec 13 '23
@felixdev9 That's not what I'm doing…
I followed the guidelines here:
dev.to/devteam/best-practices-for-...
And in this post, I literally talked about how some listicles are good:
If you think I didn't follow the guidelines, then please tell me how I can improve my posts.
That's a listicle of code snippets you have created. And your original post before editing did critique listicles.
There was no talk of listicles being shallow or meaningful.
@felixdev9 It is a listicle, and I repeat that not all listicles are bad. I followed the guidelines for listicles on dev.
It still does, too.
There was talk of listicles being shallow. None of them being meaningful, hence the update.
I apologize if my original post was unclear about the fact that not all listicles are bad before my edits. If there is a specific way that I could improve any of my posts overall, then let me know.
Why are you hiding the comments, especially those which don't align with your views?
I didn't see any reason why comments that weren't about someone who learned something or constructive criticism should be seen. If you can give me a good reason, I'll unhide them.
A solution could be - in addition to those mentioned here - to establish a trust system for authors. It would talk metrics of number of posts with content valued by readers etc. The most trusted authors would be reviewed on a regular basis and see whether they really deserve their state.
I am aware of the issues with this proposal, but I think reliability is with authors and not single articles.(in the mid or long run)
A trust system might not be as easy as it seems. I often described DEV as a welcoming, inclusive antithesis of StackOverflow's alleged meritocracy. But still a curating committee of experts and temporary, maybe elected, deputies promises to be much better than the current situation. We even have the tools. I have a "moderate post" where I can add invisible ratings to posts, apart from the obvious hearts and reactions. This additional hidden rating seems to be a privilege that could be used and given more weight for a community trust system.
If there was a reliable way to do this, it would be nice. I got downvoted once on Stack Overflow though and am now permanently banned from posting. The system can mess up a lot. Maybe it could be improved? IDK. Thanks for your opinion!
Totally agree: I have pretty much given up on this site because all I ever see are these lame "top 7 things I MUST know", followed by lists highlighting the top posts on dev.to that repeat what I just scrolled past... It's become tedious beyond measure.
I just scroll down a ways or go to the Latest or Top tabs instead.
Agreed, it’s quality over quantity. These lists almost never offer valuable data.
The lists are directly connected to people using AI to generate their content. I have commented on a similar discussion about AI that it creates a “laundromat” of content, posted again and again just for the sake of posting and not for the sake of delivering valuable information. It’s bad, truly.
Do you have any thoughts on how to counteract this? I kind of like the listicle tag idea, and just writing good content. :)
Thanks for the post and the long list of valid objections against listicle clickbait content! At least the current wave of them is easy to spot due to their generative AI aesthetic cover images and the "EVERY/MUST" keywords.
I have set my experience level to senior and tuned my watchlist with some negative tags like "ai" but it seems that we need an additional word filter to stop those EVERY/MUST listicles to appear on top of my "relevant" feed more and more often.
I agree that the problem is neither the list style nor the title or imagery, but rather the lack of research and the promotional links. If this trend goes on, DEV will become an overrated garbage page much like medium has seen better days. Then we will either need alternative forem clients or switch to another new community that is not popular enough for spammers yet.
I agree. Thanks for commenting!
I want to understand the problem better. How is the feed working? I thought it is showing in chronological descending order. I don't believe there is some smart algorithm at play, so if listicles are showing more it means more and more people are doing it.
The posts are sorted by “Relevance”, using an algorithm that sorts the posts based on your tags in a way that it thinks is good. It is too prone to lists and influenced by the post's popularity too much.
But this means that for some reason the listicles become very popular. What is the reason behind their popularity?
The algorithm probably sees a large number, put the content up a bit higher, and then people see it and click on it because of the emoji and FOMO. Then, they like the post, it gets higher and higher…
Plus the number in the title and the collection of things which feels as if you are getting "more for the price of one" bargain. I think the reason why such post is liked more is because it's not a sequence in which any step may brake, but a list of things and only one has to work in order for a person to have a somewhat positive reaction.
dev.to is a fairly free, non-regulated market for writers: you can't make people not write something in particular, and you can't control (educate) readers either not to fall for clickbaits, i.e. click/react to listicles.
If you wish for something more elevated, then you need a writing space where these kind of things are controled. Take, for example, a look at leaddev.com - not anyone can write there, only a closed (controlled ) circle.
That's how you get the quality you want. But you sarcifice freedom / openness :)
Interesting point of view, thanks for sharing!!
I guess such activities are sort of also driven by the dev.to business model. I mean, traffic might be crucial; hence, more posts are better. But that impacts quality and, in the long term, potentially less and less user engagement.
I would consider points like this:
Finally, maybe create some few meetings to discuss it? For example at vibehut.io/chat?roomId=63642ebb6f1...
I've been adding emojis to my trace messages. (I guess this is OT) It's a really good way to recognize which source file, or subsystem, a given trace message comes from. Just wander thru the emoji panel, and find one that's vaguely like your subsystem. It doesn't have to be appropriate, it could just be one that you like for some reason, or a cynical joke, or a color. Use 🧐 for warnings and 😏, 🤦♀️ or 🤬 for error messages. I'm using 🐎 for when it's 'running' and 📫📪📬📭 for different parts of message passing. Or ✉️ 📦 📨 . They don't have to be dorky, 🟥 🟧 🟡 🟢 🏁 🇨🇮 🏛️ ⏲️ 📡 🧱 🔬☢️ ❌ 🔽 ⬆️ . Meanwhile, the rest of Unicode has tons of monochrome icons ❖ ✓ ∞ 【 】 ♖ ⿶♫ ʢ ᴫ ♴ ♗ ♙ ♂︎ ⚢ ⎈ ⏣ ⠳ ▨ ▛ ◕ ◉ . Time to use them.
LOL, that's a fun idea! I might have to try it myself sometime.
As someone who writes a lot of listicles on dev, this is a fair critique and a hilarious way of delivering it 😂
At the same time, I do have to push back a bit. When I write a listicle I do a lot of work that ends up being useful for the devs reading it - which is why so many like and save them.
I go through a bunch of repos, find and categorize the best ones, explain them in simple terms and package them in an aesthetic and easy-to-read way.
If I can bring attention to my repo & deliver value to devs at the same time, I see it as a win-win.
Are there too many listicles? Probably.
Do they have clickbaity titles? Everything online does.
It's definitely something worth discussing and maybe a listicle tag would be a good way of filtering them to those who want to see them. But, don't discount the value Devs are getting from these. There's a reason they do well on the platform even if you personally don't like them.
@uliyahoo Thanks for sharing your opinion! 🥰
I share some listicles too, but I make sure that they follow the dev.to listicle guidelines here:
dev.to/devteam/best-practices-for-...
As stated in the post, there are right and wrong ways to do listicles, and not all of them are bad.
Now, I'm going to check out yours! 😏
We should have a way of filtering out these articles or flagging them, this site used to be a lot better now it's mostly useless stuff, the only articles that I read and ones publish by some people that I know and follow, most of the "top stories" are hot garbage
This has been the most valuable post I have seen by far. Why? Because it aims to make this community better. How could there possibly be 25 repos I can't live with out? It would take me 2hrs+ to actually dissect these listicals into real data that could help me as a developer. Thank you for bringing this up, I really hope they can mitigate what feels like spam.
Thanks for your opinion! I am glad that you liked my post!
Hehe, I’m about to post a (hopefully truly helpful) listicle tho. It’s about some of the best podcasts for Devs to listen to. It’s prob going to be titled something like “The Best Podcasts for Techies to listen to”. YK what I’m saying? No number there! :)
I'll be sure to check it out!
dev.to admin should be able to help combat the click bait.
Agreed.
So you created one more listicle to convince people not to create listicles? 🤔📝😅
LOL, yes, for fun. :D
Hey dude - nice article :) Like it. I do think that there are some articles that are helpful, but the ones you showed were definite examples. Great post.
Thanks!
This is still a listicle, but it's not bad
LOL Thanks
I can't say I don't agree with you. While there are major parts of this site that contain good and high quality content, Dev.to does sometimes feel like a "developer focused Instagram", if you will.
I understand completely. I wish the content could be better.
The 1000-word threshold is a good one to filter on.
Not sure if I would agree. What if someone had good content that was 1000+ words long? It might be lengthy, in depth, and useful! Thanks for your opinion, though, it has made me think. :)
Agreed 💯 but on the other hand, some people create what attracts attention. Listicles do, so people make them.
In which case, people should make real content. :D
I was just thinking this right before seeing this article! Wouldn't mind just reading about someone's experiences in the field without a list.
Yes, exactly. I'm glad you found the post interesting!
Did you post a comment in the wrong place??