@ WoundedLamb I was about creating a topic on this. I've noticed that for over a month now. Just look at the screenshots below, they've spammed the whole forum

flamingREED:


Unfortunately for them, any Nairalander who is active in this section is way more intelligent than they can disinform.

so true

VickyRotex:


LOL. Supreme leader sounds like geng leader

Hallos team lead,

Several approaches to automating this.

E.g., use of scripts and pointers.

Their AI/ML tools just needs to learn the pattern. Remember there is (are) a pattern that's why we could tell too.

1. Tool learns
2. Implement auto deletion with scripts.
3. If same account makes a post again, implement auto-deletion of account after a certain threshold or just instant deletion of account.

There'll of course be some false positives ab initio, but that's the beauty of AI/ML. It'll keep learning and improving.

What do you think?

Unless again, they're bots owned/known to the owner of the forum. Eye didn't say anything.

ML is a good suggestion and it will be relatively easy for Seun to implement cause there are already known networks that can handle such cases and Nairaland runs on Python (as I learned) so he'll only need to install the Anaconda framework to kick off. However, he will need to feed the ML network with more data than Nairaland presently collects if he really wants detect these guys. Again, it will still be somewhere tricky cause even with the best binary classification algorithms, genuine posts can still easily be classified as spam.

flamingREED:


Unfortunately for them, any Nairalander who is active in this section is way more intelligent than they can disinform.

I think they are more interested in feeding the internet with their version so as to influence future search results.

accounts2boku:
@ WoundedLamb I was about creating a topic on this.
I've noticed that for over a month now.
Just look at the screenshots below, they've spammed the whole forum

It's excessive. Anyone that logs in late at night (or those that stay abroad) can testify to the fact that these guys completely take up the forum at night. I think the timing is deliberate cause the aim is not to engage people or even get audience now. The aim is to feed the internet with enough false information to influence future search results.

WoundedLamb:


ML is a good suggestion and it will be relatively easy for Seun to implement cause there are already known networks that can handle such cases and Nairaland runs on Python (as I learned) so he'll only need to install the Anaconda framework to kick off. However, he will need to feed the ML network with more data than Nairaland presently collects if he really wants detect these guys. Again, it will still be somewhere tricky cause even with the best binary classification algorithms, genuine posts can still easily be classified as spam.

Agreed that genuine posts can still get classified as spam and those are the false positives that the forum will have to ruffle with for a while. But with detailed data ingestion and analysis, the predictive model will get better over time and the side effects can be minimal.

Also if it takes sacrificing some genuine posts for a while I think it's worth the sacrifice or worth the cause. (Of which those can be auto restored anyways)
Learning, adapting, and improving on the pattern is really key to making it an iterative process.

I like to think the owner of this forum knows exactly what to do and maybe just maybe he's working on it but we're yet to see it's effect. I like to think so, else........!!!

VickyRotex:


Agreed that genuine posts can still get classified as spam and those are the false positives that the forum will have to ruffle with for a while. But with detailed data ingestion and analysis, the predictive model will get better over time and the side effects can be minimal.

Also if it takes sacrificing some genuine posts for a while I think it's worth the sacrifice or worth the cause. (Of which those can be auto restored anyways)
Learning, adapting, and improving on the pattern is really key to making it an iterative process.

I like to think the owner of this forum knows exactly what to do and maybe just maybe he's working on it but we're yet to see it's effect. I like to think so, else........!!!

Hhmm... great! Our leader is very much on top of this!

But are you suggesting training the system with live data? I think the Chinese would have finished building their empire before that yields any positive result! To really combat these guys using ML, Seun will need a pre-trained model with the weights stored in the DB. In other words, he needs to have a collection of already classified texts (spam and genuin) and pass them through the neural network till the optimal weights per node is calculated. He can then store this weights in the DB so that the system can use this to detect spam posts. Apart from the text itself, I think training with log details like users country (which will eventually be collected using HTML3 geolocation API on the live server), session time, etc. will help ensure reliability. But like I said, there'll still a be a very few genuine post that will fall through the cracks.

Yes, Seun might be working on this already but you can also reach out to him to make suggestions or even help out if possible

WoundedLamb:


Hhmm... great! Our leader is very much on top of this!

But are you suggesting training the system with live data? I think the Chinese would have finished building their empire before that yields any positive result! To really combat these guys using ML, Seun will need a pre-trained model with the weights stored in the DB. In other words, he needs to have a collection of already classified texts (spam and genuin) and pass them through the neural network till the optimal weights per node is calculated. He can then store this weights in the DB so that the system can use this to detect spam posts. Apart from the text itself, I think training with log details like users country (which will eventually be collected using HTML3 geolocation API on the live server), session time, etc. will help ensure reliability. But like I said, there'll still a be a very few genuine post that will fall through the cracks.

Yes, Seun might be working on this already but you can also reach out to him to make suggestions or even help out if possible

lol
Build an empire kwa

Apt! Yes, I agree with you. Although there are average data to build the model, it will be time wasting to begin from scratch when there are existing ones to leverage.  The pre-trained models is way to go and ofcourse there are several of them from other libraries, like earlier mentioned this isnt the first forum with such (except that these ones are lala's lol) so Seun wouldn't need to build one from scratch to clamp down on this.

I mean, the deltas will surely need to be mapped as it will never be a perfect model for this use case but better as a starting point and live data will need to be ingested to reduce the obsolescence.

Also note, pre-trained model would still not get rid of the false positives(genuine post errors). Having a model to build on is one thing but being able to train it to meet your needs is another.

Training with log details or session details isn't a bad idea either. I'd push back on that (for other reasons) if NL wasn't already collecting these info anyways. Moreover it's faster than building out a new model, but more susceptible/prone to errors.

Let me pretend I didn't see your last line. Team lead, this is your calling. Accept it wholeheartedly!

Ayam a learner!

VickyRotex:


lol
Build an empire kwa

Apt! Yes, I agree with you. Although there are average data to build the model, it will be time wasting to begin from scratch when there are existing ones to leverage.  The pre-trained models is way to go and ofcourse there are several of them from other libraries, like earlier mentioned this isnt the first forum with such (except that these ones are lala's lol) so Seun wouldn't need to build one from scratch to clamp down on this.

I mean, the deltas will surely need to be mapped as it will never be a perfect model for this use case but better as a starting point and live data will need to be ingested to reduce the obsolescence.

Also note, pre-trained model would still not get rid of the false positives(genuine post errors). Having a model to build on is one thing but being able to train it to meet your needs is another.

Training with log details or session details isn't a bad idea either. I'd push back on that (for other reasons) if NL wasn't already collecting these info anyways. Moreover it's faster than building out a new model, but more susceptible/prone to errors.

Let me pretend I didn't see your last line. Team lead, this is your calling. Accept it wholeheartedly!

Ayam a learner!

Voilà... false positive can only be reduced. Training can be done with the spam threads already created on NL so far (though the small size of the sample (data rows) can easily lead to overfitting if used continuously ). I'm only advocating for more features (data columns such as the logs mentioned above) just to bring up up dimensions a little bit without invoking the curse of dimensionality. I know how we feel when these apps take more info than we think is required but this one would be for a good course.

I don't think Nairaland take geolocation details, your browser would have detected that. Unlike major forums out there, Nairaland doesn't really streamline user experience to reflect their location. The argument would be that it doesn't need that seeing that it doesn't make location based suggestions. But then again, some of us out here sometimes get confused with the time display.

Like I said, Seun needs your help regarding these Chinese guys. Nairaland needs you, Madam Vicky. Please, help us! This forum belongs to all of us and not only Seun. Please!

_{Where you on Nairaland during the dark age (around 2014/15 when the site collapsed for days and everyone had to go to other social networks to ask questions)? Do you want that to happen again?}

WoundedLamb:


Voilà... false positive can only be reduced. Training can be done with the spam threads already created on NL so far (though the small size of the sample (data rows) can easily lead to overfitting if used continuously ). I'm only advocating for more features (data columns such as the logs mentioned above) just to bring up up dimensions a little bit without invoking the curse of dimensionality. I know how we feel when these apps take more info than we think is required but this one would be for a good course.

I don't think Nairaland take geolocation details, your browser would have detected that. Unlike major forums out there, Nairaland doesn't really streamline user experience to reflect their location. The argument would be that it doesn't need that seeing that it doesn't make location based suggestions. But then again, some of us out here sometimes get confused with the time display.

Like I said, Seun needs your help regarding these Chinese guys. Nairaland needs you, Madam Vicky. Please, help us! This forum belongs to all of us and not only Seun. Please!

_{Where you on Nairaland during the dark age (around 2014/15 when the site collapsed for days and everyone had to go to other social networks to ask questions)? Do you want that to happen again?}

Correct! Scatter our head lol

Good point! In bold: exactly one reason I'd push back.
Curse of dimensionality and law of trade-offs brouhaha.
Sacrificing privacy for security has always been short-term resort. Short-term indeed

It does collect actually, to an extent though; not in the real sense of geolocation permission to pin down an exact location  nor enough details to push through a model as this one. It'd require a mix of other things like the features you mentioned earlier.

Remember the application knows the IP addresses of it's users. So this can be used to narrow down your ISPs but not your exact location. Use of VPN also circumvents this effort though. So like I said, analyzing this independently, wont lead to making that much of a headway.

But I do think it's somewhat sufficient in addition to other data that'll be used. I mean it doesn't need a user's exact location to address this.

Oh and remember privacy law appears to be more of a mirage so don't be surprised if if if.......... let me rest my case.

The time location is a minute part of the series of confusion this site houses. And let's not even get into the nitty-gritty of how this forum manages users sessions. OMG Seun will soon ban my account. Lemme be going.

_{Na real dark age. lol. I was a member but it was one of those period I was off NL for a while so didn't realize until I saw threads about it. You can't guilt trip me with that.}

So Oga/Madam, PLEASE dont deny this calling. I'm only here to cheer you on.

VickyRotex:


Correct! Scatter our head lol

Good point! In bold: exactly one reason I'd push back.
Curse of dimensionality and law of trade-offs brouhaha.
Sacrificing privacy for security has always been short-term resort. Short-term indeed

It does collect actually, to an extent though; not in the real sense of geolocation permission to pin down an exact location  nor enough details to push through a model as this one. It'd require a mix of other things like the features you mentioned earlier.

Remember the application knows the IP addresses of it's users. So this can be used to narrow down your ISPs but not your exact location. Use of VPN also circumvents this effort though. So like I said, analyzing this independently, wont lead to making that much of a headway.

But I do think it's somewhat sufficient in addition to other data that'll be used. I mean it doesn't need a user's exact location to address this.

Oh and remember privacy law appears to be more of a mirage so don't be surprised if if if.......... let me rest my case.

The time location is a minute part of the series of confusion this site houses. And let's not even get into the nitty-gritty of how this forum manages users sessions. OMG Seun will soon ban my account. Lemme be going.

_{Na real dark age. lol. I was a member but it was one of those period I was off NL for a while so didn't realize until I saw threads about it. You can't guilt trip me with that.}

So Oga/Madam, PLEASE dont deny this calling. I'm only here to cheer you on.

Lol... ma, what are you are you doing on Nairaland that you're hiding like this?

Yeah... You are absolutely right! I wasn't thinking about server-side location queries based on IP address. That's dependent on pre-stored data in the DB and does not really offer much when location is a big deal cause, like you said, the IP's may also be shared across a region and the database itself isn't really as immutable as we'd like it to be. I was rather focused on HTML geolocation API which does not rely on IP network databases for determining location though it would first ask for browser permission (such a polite technology). I still doubt Seun is collecting IP details. His site was never designed to be international (where location tracking would have played a great role).

That's about that. Regarding the input to the ANN you're designing for Seun, I was suggesting location cause I was thinking of a probabilistic neural networks (PNN) as against a multi layered perceptron (cause even if the output of a multilayered perceptron is between 1 and 0 based on the activation function adopted, it would still be risky to interpret that as 'probability'..... right?). I believe if these guys have been connecting from China (or any other specific region for that matter) and such data dimension is added to the input, the node will be adequately weighted after series of back propagations in the PNN and the single output neuron will produce values ranging from zero to one. This values can then be interpreted as probabilistic values instead a hard classification. This way, threads from a region that has produced several spam threads in the past will slightly increase the probability over time. The probabilistic values can then be passed on to a conventional code block with variable tolerance threshold determined by Seun himself and the code block makes the final decision. This approsch comes with the PNN overheads like speed and memory requirements for the mandatory pattern and summation layer processing but it kinda allows him to increase or decrease the strictness of the system within a given period by altering the threshold (OK.... forgive my poor design ).

But then again, these guys would be changing their location everyday using VPN so all that would be far more theoretical than practical. Really, technology is technology's problem. Lol. Whichever way, ML will still reduce this menace to the barest minimum if not completely (we can sacrifice a few genuin posts for that, right?).

You've said yourself that NL is the most unsophisticated successful websites out there, why not lend a hand? You can't sit back and watch us drown when you have a solution! I will create a thread calling on other NL members to plead with you!

how can strange account appear every midnight.

Trump supporters are always hallucinating.

@AIlahuAkbar, I saw your mention. I just don't want to be commentating on their threads. Their names are mostly in Piyin (Chinese written with the European alphabet) or just gibberish like "v7yrs7mbzwef56g". The one you quoted is David Guo. Guo is the Chinese word for "country". If you come online at night (Nigerian time), you'd notice that they'd completely fill up the entire New Threads page as someone shared above and a lot of them would be accounts created that minute while others would be old accounts that have been posting the same thing every night (multiple threads per night) since creation. They don't comment on other people's threads cause their number of posts is always equal to their number of threads. The mods have been deleting and blocking but it seems they are tired. It could be annoying cause my early evening is Nigeria's night so when I come online to see new threads, I only see them.

kelvinslim:
how can strange account appear every midnight.

Scan through the thread, you'd get the story of what has been happening. You can observe for yourself.

Cyberterror:
Trump supporters are always hallucinating.

You are Cyber Terror and the first thing that comes to your mind when you read this thread is Trump's politics? Instead of writing off things so offhandedly, why not ask questions or observe yourself and decide. In addition to the pics already shared, below are some screenshots I took myself on two different occasions. They still came last night and new ones will come tonight. They occupy the forum the entire night and they are relentless.

@Woundedlamb
Seun will be somewhere celebrating how nairaland has up to 5 million registered members not knowing some bots and hacker's are creating multiple accounts every night.
I doubt if nairaland alone has up to 500 thousand active members.
I personally know someone here that has more than 3 thousand monikers, he's always active in the politics section

AIlahuAkbar:
@Woundedlamb
Seun will be somewhere celebrating how nairaland has up to 5 million registered members not knowing some bots and hacker's are creating multiple accounts every night.
I doubt if nairaland alone has up to 500 thousand active members.
I personally know someone here that has more than 3 thousand monikers, he's always active in the politics section

Lol @the first line.

Actually, I think he's aware of this. I think so cause the mods have made some efforts to combat these guys by deleting their threads. However, like I said, they are relentless.

WoundedLamb:


Oh... I think I already know how Vicky handled the situation! She started crying and shouting at the spy "leave us alone nah!" (in Nigerian accent). Lol

Meanwhile, igbesachick is probably the spy here. For history sake, note that I'm the smart one who who detected the mole!

He is one of those released prisoners in China that the CCP use for construction job outside China as condition for hailing emperor Xi Jinping and also to spread China propaganda wherever they are.

Yahyacovid19:


He is one of those released prisoners in China that the CCP use for construction job outside China as condition for hailing emperor Xi Jinping and also to spread China propaganda wherever they are.

chinese prisoners in africa are treated as whites and called"master". so, you guys are really fvcked up.!

even a chinese prisoner can enjoy such a status in your race, what about a chinese a little better than a prisoner? such as a 21 year old, newly graduated from a third rate college , chinese young kid ? that is your master Wang or Master zhang, with a pair of glasses , speaking some sort of english.

you stupid shiet, you think you are humiliating chinese, but you are lowering your race's status.

Oh! I thought it was just me noticing these "black-propaganda" threads. The trend has been on for a while and all I do is to scroll pass.

accounts2boku:
@ WoundedLamb I was about creating a topic on this.
I've noticed that for over a month now.
Just look at the screenshots below, they've spammed the whole forum

Guy what's up bro I just called u.
Abt Man-G