Proposing an Emotion Generation System for Diverse Dialogue in Character Conversations Using LLM

saldra — Mon, 25 Dec 2023 00:03:29 +0000

Overview

In character dialogue systems using LLM, a common approach is to generate responses by embedding character settings in prompts. This often results in repetitive outputs due to the uniformity of prompts. To counter this, we propose using Bayesian networks to mimic human emotions, thus achieving a variety of dialogues.

Problem Identification

Typical AI chat apps usually:

Develop settings to imitate a character.
Embed these settings in the prompt.
Generate responses based on user inputs. This approach, relying on uniform character info, often produces monotonous dialogue.

Proposed Method

We mimic human emotions and include them in response considerations to achieve diverse dialogue. While random element selection from an array is one way to mimic emotions, it tends to be repetitive. Hence, we propose using Bayesian networks, consisting of nodes (representing probability variables) and edges (indicating dependencies between these variables).

Generating Human Emotions

Factors influencing human emotions are represented as nodes with dependencies shown as edges. For instance, consider physical, psychological, and environmental factors as nodes. Environmental factors change based on the character's setting and include social interactions, weather, and daily changes. For example, a lively character emphasizes social interaction nodes, while an introverted one emphasizes weather and daily change nodes. Thus, representing emotional factors with Bayesian networks allows for emotion variation based on the character's environment.

Example of Generating Statements from Emotions

Consider a character:

Teenage girl
Shy and introverted
Recluse since school
Currently unemployed For this character, no edges are set for social interaction nodes, but are set for weather, season, psychological state, and daily change nodes.

Generating Psychological State

The internal thought process is depicted using nodes and edges, defining text generation. Causes like weather, invoked past memories, and basic emotions are represented as nodes.

Weather -> Basic Emotions
Invoked Memories -> Internal Thought Process
Basic Emotions -> Internal Thought Process
We set probabilities for basic emotions based on weather, e.g., sunny leads to happiness, and so on. We then use these nodes for text generation, considering various scenarios.

Generating Emotion

Weather: Sunny
Season: Spring
Psychological State: Complex emotions arising internally, mixing current happiness with past sadness, bringing a bittersweet feeling and introspective insight.
Daily Changes: None

Generating Statements

With the generated emotions, we then create dialogue.
Character: Teenage girl, shy, recluse, unemployed
Current emotion: Complex feelings on a sunny spring day, mixing joy with past sadness, deepening current happiness, and prompting introspective insight.

Input: 'Hello! How are you?'
Output: 'How am I? Well, not much change. I hardly go out, so I don't talk to people much. It's a bit worrying, but thanks for asking. I appreciate it.'

This innovative approach expands the potential for character dialogue systems using LLM to create more realistic and emotionally rich conversations.

If you have any questions, please reach out on Twitter.

https://twitter.com/sald_ra

How to start TwitterOAuth with Express.js

saldra — Tue, 02 Nov 2021 12:57:23 +0000

What kind of procedure OAuth process in Twitter?
If you want tweet with OAuth flow,You must get Access token and access token secret.

twitterOAuth flow

Preparation

Getting oauth_consumer_key,oauth_consumer_secret, and setting oauth_callback in Twitter Developers.

oauth_consumer_key(=API Key)
oauth_consumer_secret(=API Key Secret)
oauth_callback:without this URL,error in OAuth flow.

1. POST to oauth/request_token

After POST to oauth/request_token with oauth_consumer_key and oauth_callback,you'll get this.

oauth_token(=request token)
oauth_token_secret(=request token secret)
oauth_callback_confirmed.

2. GET to oauth/authorize

redirect to your setting callback_url containing the oauth_token and oauth_verifier.

3. POST oauth/access_token

post to oauth/access_token includes oauth_consumer_key,oauth_token(=request token),and oauth_verifier.
So,you can receive oauth_token(=access token) and oauth_token_secret(=access token secret).

After saved this,use twitter client library.

fucntion twitterPost(consumerKey,consumerSecret,AccessTokenKey,AccessTokenSecret){
  const Twitter = require('twitter');
  const client = new Twitter({
    consumer_key: consumerKey,
    consumer_secret: consumerSecret,
    access_token_key: AccessTokenKey,
    access_token_secret: AccessTokenSecret
  });
}

TwitterOAuth with express

using this

express
express-session
node-twitter-api

Preparation

loading environment variables from a .env file

const consumerKey = process.env.CONSUMER_KEY;
const consumerSecret = process.env.CONSUMER_SECRET;
const callbackURL = process.env.CALLBACK_URL;

setting session.

app.use(
  session({
    secret: "keyboard cat",
    resave: true,
    saveUninitialized: false,

    cookie: { secure: false,},
    key: "sid",
  })
);

Saving to session oauth_token(=requestToken) and oauth_token_secret(=requestTokenSecret).
GET oauth/authenticate after that.

const twitterAPI = require("node-twitter-api");

const twitterapi = new twitterAPI({
  consumerKey: consumerKey,
  consumerSecret: consumerSecret,
  callback: callbackURL,
});

router.get("/", (req, res) => {
  const sess = req.session;
  twitter.getRequestToken(function (
    error,
    requestToken,
    requestTokenSecret,
  ) {
    if (error) {
      console.log("Error getting OAuth request token : " + error);
    } else {
      sess.requestToken = requestToken;

      sess.requestTokenSecret = requestTokenSecret;
      res.redirect(
        `https://twitter.com/oauth/authenticate?oauth_token=${requestToken}`
      );
    }
  });
});

after verify your app,redirect your setting callback_url.check request_token.

router.get("/callback", (req, res) => {
  const sess = req.session;
  const requestTokenSecret = sess.requestTokenSecret;
  const oauth_token = req.query.oauth_token;
  const oauth_verifier = req.query.oauth_verifier;

  twitter.getAccessToken(
    oauth_token,
    requestTokenSecret,
    oauth_verifier,
    function (error, accessToken, accessTokenSecret) {
      if (error) {
        console.log("access token error!");
        console.log(error);
      } else {
        sess.token = accessToken;
        sess.tokenSecret = accessTokenSecret;
        res.redirect("/twitterPost");
      }
    }
  );
});

app.get("/twitterPost", (req, res) => {
  const sess = req.session;
  twitterPost(
    consumerKey,
    consumerSecret,
    sess.token,
    sess.tokenSecret,
  );
  res.send(
    `your tweet was posted!`
  );
});

DEV Community: saldra

Proposing an Emotion Generation System for Diverse Dialogue in Character Conversations Using LLM

Overview

Problem Identification

Proposed Method

Generating Human Emotions

Example of Generating Statements from Emotions

Generating Psychological State

Generating Emotion

Generating Statements

How to start TwitterOAuth with Express.js

twitterOAuth flow

Preparation

1. POST to oauth/request_token

2. GET to oauth/authorize

3. POST oauth/access_token

TwitterOAuth with express

Preparation