Twitch Bot for generating messages based on what it learned from chat
When the bot has started, it will start listening to chat messages in the channel listed in the settings.json file. Any chat message not sent by a denied user will be learned from. Whenever someone then requests a message to be generated, a Markov Chain will be used with the learned data to generate a sentence. Note that the bot is unaware of the meaning of any of its inputs and outputs. This means it can use bad language if it was taught to use bad language by people in chat. You can add a list of banned words it should never learn or say. Use at your own risk.
Whenever a message is deleted from chat, it's contents will be unlearned at 5 times the rate a normal message is learned from. The bot will avoid learning from commands, or from messages containing links.
To explain how the bot works, I will provide an example situation with two messages that are posted in Twitch chat. The messages are:
Curly fries are the worst kind of fries Loud people are the reason I don't go to the movies anymore
Let's start with the first sentence and parse it like the bot will. To do so, we will split up the sentence in sections of keyLength + 1 words. As keyLength has been set to 2 in the Settings section, each section has 3 words.
Curly fries are the worst kind of fries
[Curly fries:are]
[fries are:the]
[are the:worst]
[the worst:kind]
[worst kind:of]
[kind of:fries]For each of these sections of three words, the last word is considered the output, while all other words it are considered inputs. These words are then turned into a variation of a Grammar:
"Curly fries" -> "are"
"fries are" -> "the"
"are the" -> "worst"
"the worst" -> "kind"
"worst kind" -> "of"
"kind of" -> "fries"This can be considered a mathematical function that, when given input "the worst", will output "kind".
In order for the program to know where sentences begin, we also add the first keyLength words to a seperate Database table, where a list of possible starts of sentences reside.
This exact same process is applied to the second sentence as well. After doing so, the resulting grammar (and our corresponding database table) looks like:
"Curly fries" -> "are"
"fries are" -> "the"
"are the" -> "worst" | "reason"
"the worst" -> "kind"
"worst kind" -> "of"
"kind of" -> "fries"
"Loud people" -> "are"
"people are" -> "the"
"the reason" -> "I"
"reason I" -> "don't"
"I don't" -> "go"
"don't go" -> "to"
"go to" -> "the"
"to the" -> "movies"
"the movies" -> "anymore"and in the database table for starts of sentences:
"Curly fries"
"Loud people"Note that the | is considered to be "or". In the case of the bold text above, it could be read as: if the given input is "are the", then the output is either "worst" or "reason".
In practice, more frequent phrases will have higher precedence. The more often a phrase is said, the more likely it is to be generated.
When a message is generated with !generate, a random start of a sentence is picked from the database table of starts of sentences. In our example the randomly picked start is "Curly fries".
Now, in a loop:
- The output for the input is generated via the grammar.
- And the input for the next iteration in the loop is shifted:
- Remove the first word from the input.
- Add the new output word to the end of the input.
So, the input starts as "Curly Fries". The output for this input is generated via the grammar, which gives us "are". Then, the input is updated. "Curly" is removed, and "are" is added to the input. The new input for the next iteration will be "Fries are" as a result. This process repeats until no more words can be generated, or if a word limit is reached.
A more programmatic example of this would be this:
# This initial sentence is either from the database for starts of sentences,
# or from words passed in Twitch chat
sentence = ["Curly", "fries"]
for i in range(sentence_length):
# Generate a word using last 2 words in the partial sentence,
# and append it to the partial sentence
sentence.append(generate(sentence[-2:]))It's common for an input sequence to have multiple possible outputs, as we can see in the bold part of the previous grammar. This allows learned information from multiple messages to be merged into one message. For instance, some potential outputs from the given example are
Curly fries are the reason I don't go to the movies anymore
or
Loud people are the worst kind of fries
Chat members can generate chat-like messages using the following commands (Note that they are aliases):
!generate [words]
!g [words]Example:
!g CurlyResult (for example):
Curly fries are the reason I don't go to the movies anymore- The bot will, when given this command, try to complete the start of the sentence which was given.
- If it cannot, an appropriate error message will be sent to chat.
- Any number of words may be given, including none at all.
- Everyone can use it.
Furthermore, chat members can find a link to How it works by using one of the following commands:
!ghelp
!genhelp
!generatehelpThe use of this command makes the bot post this message in chat:
Learn how this bot generates sentences here: https://github.com/CubieDev/TwitchMarkovChain#how-it-works
All of these commands can be whispered to the bot account, or typed in chat. To disable the bot from generating messages, while still learning from regular chat messages:
!disableAfter disabling the bot, it can be re-enabled using:
!enableChanging the cooldown between generations is possible with one of the following two commands:
!setcooldown <seconds>
!setcd <seconds>Example:
!setcd 30Which sets the cooldown between generations to 30 seconds.
All of these commands must be whispered to the bot account.
Moderators (and the broadcaster) can modify the blacklist to prevent the bot learning words it shouldn't.
To add word to the blacklist, a moderator can whisper the bot:
!blacklist <word>Similarly, to remove word from the blacklist, a moderator can whisper the bot:
!whitelist <word>And to check whether word is already on the blacklist or not, a moderator can whisper the bot:
!check <word>This bot is controlled by a settings.json file, which has the following structure:
{
"Host": "irc.chat.twitch.tv",
"Port": 6667,
"Channel": "#<channel>",
"Nickname": "<name>",
"Authentication": "oauth:<auth>",
"DeniedUsers": ["StreamElements", "Nightbot", "Moobot", "Marbiebot"],
"AllowedUsers": [],
"Cooldown": 20,
"KeyLength": 2,
"MaxSentenceWordAmount": 25,
"MinSentenceWordAmount": -1,
"HelpMessageTimer": 18000,
"AutomaticGenerationTimer": -1,
"WhisperCooldown": true,
"EnableGenerateCommand": true,
"SentenceSeparator": " - ",
"AllowGenerateParams": true,
"GenerateCommands": ["!generate", "!g"]
}| Parameter | Meaning | Example |
|---|---|---|
Host |
The URL that will be used. Do not change. | "irc.chat.twitch.tv" |
Port |
The Port that will be used. Do not change. | 6667 |
Channel |
The Channel that will be connected to. | "#CubieDev" |
Nickname |
The Username of the bot account. | "CubieB0T" |
Authentication |
The OAuth token for the bot account. | "oauth:pivogip8ybletucqdz4pkhag6itbax" |
DeniedUsers |
The list of (bot) accounts whose messages should not be learned from. The bot itself it automatically added to this. | ["StreamElements", "Nightbot", "Moobot", "Marbiebot"] |
AllowedUsers |
A list of users with heightened permissions. Gives these users the same power as the channel owner, allowing them to bypass cooldowns, set cooldowns, disable or enable the bot, etc. | ["Michelle", "Cubie"] |
Cooldown |
A cooldown in seconds between successful generations. If a generation fails (eg inputs it can't work with), then the cooldown is not reset and another generation can be done immediately. | 20 |
KeyLength |
A technical parameter which, in my previous implementation, would affect how closely the output matches the learned inputs. In the current implementation the database structure does not allow this parameter to be changed. Do not change. | 2 |
MaxSentenceWordAmount |
The maximum number of words that can be generated. Prevents absurdly long and spammy generations. | 25 |
MinSentenceWordAmount |
The minimum number of words that can be generated. Might generate multiple sentences, separated by the value from SentenceSeparator. Prevents very short generations. -1 to disable. |
-1 |
HelpMessageTimer |
The amount of seconds between sending help messages that links to How it works. -1 for no help messages. Defaults to once every 5 hours. | 18000 |
AutomaticGenerationTimer |
The amount of seconds between automatically sending a generated message, as if someone wrote !g. -1 for no automatic generations. |
-1 |
WhisperCooldown |
Allows the bot to whisper a user the remaining cooldown after that user has attempted to generate a message. | true |
EnableGenerateCommand |
Globally enables/disables the generate command. | true |
SentenceSeparator |
The separator between multiple sentences. Only relevant if MinSentenceWordAmount > 0, as only then can multiple sentences be generated. Sensible values for this might be ", ", ". ", " - " or " ". |
" - " |
AllowGenerateParams |
Allow chat to supply a partial sentence which the bot finishes, e.g. !generate hello, I am. If false, all values after the generation command will be ignored. |
true |
GenerateCommands |
The generation commands that the bot will listen for. Defaults to ["!generate", "!g"]. Useful if your chat is used to commands with ~, -, /, etc. |
["!generate", "!g"] |
Note that the example OAuth token is not an actual token, but merely a generated string to give an indication what it might look like.
I got my real OAuth token from https://twitchapps.com/tmi/.
You may add words to a blacklist by adding them on a separate line in blacklist.txt. Each word is case insensitive. By default, this file only contains <start> and <end>, which are required for the current implementation.
Words can also be added or removed from the blacklist via whispers, as is described in the Moderator Command section.
- Python 3.6+
- Module requirements
- Install these modules using
pip install -r requirements.txtin the commandline.
- Install these modules using
Among these modules is my own TwitchWebsocket wrapper, which makes making a Twitch chat bot a lot easier. This repository can be seen as an implementation using this wrapper.
My gratitude is extended to the following contributors who've decided to help out.
- @DoctorInsano - Several small fixes and improvements in v1.0.
- @justinrusso - Several features, refactors and fixes, that represent the core of v2.0 and v2.1.
- TwitchAIDungeon
- TwitchGoogleTranslate
- TwitchCubieBotGUI
- TwitchCubieBot
- TwitchRandomRecipe
- TwitchUrbanDictionary
- TwitchRhymeBot
- TwitchWeather
- TwitchDeathCounter
- TwitchSuggestDinner
- TwitchPickUser
- TwitchSaveMessages
- TwitchMMLevelPickerGUI (Mario Maker 2 specific bot)
- TwitchMMLevelQueueGUI (Mario Maker 2 specific bot)
- TwitchPackCounter (Streamer specific bot)
- TwitchDialCheck (Streamer specific bot)
- TwitchSendMessage (Meant for debugging purposes)
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent