All Projects → thisandagain → Troll

thisandagain / Troll

Licence: other
Language sentiment analysis and neural networks... for trolls.

Programming Languages

javascript
184084 projects - #8 most used programming language

Projects that are alternatives of or similar to Troll

Senti4SD
An emotion-polarity classifier specifically trained on developers' communication channels
Stars: ✭ 41 (-87.58%)
Mutual labels:  sentiment-analysis, sentiment
sentiment-analysis-using-python
Large Data Analysis Course Project
Stars: ✭ 23 (-93.03%)
Mutual labels:  sentiment-analysis, sentiment
brand-sentiment-analysis
Scripts utilizing Heartex platform to build brand sentiment analysis from the news
Stars: ✭ 21 (-93.64%)
Mutual labels:  sentiment-analysis, sentiment
Sentiment
AFINN-based sentiment analysis for Node.js.
Stars: ✭ 2,469 (+648.18%)
Mutual labels:  sentiment-analysis, sentiment
stock-news-sentiment-analysis
This program uses Vader SentimentIntensityAnalyzer to calculate the news headline overall sentiment for a stock
Stars: ✭ 21 (-93.64%)
Mutual labels:  sentiment-analysis, sentiment
Whatsapp-analytics
performing sentiment analysis on the whatsapp chats.
Stars: ✭ 20 (-93.94%)
Mutual labels:  sentiment-analysis, sentiment
stansent
No description or website provided.
Stars: ✭ 16 (-95.15%)
Mutual labels:  sentiment-analysis, sentiment
Stocksight
Stock market analyzer and predictor using Elasticsearch, Twitter, News headlines and Python natural language processing and sentiment analysis
Stars: ✭ 1,037 (+214.24%)
Mutual labels:  sentiment-analysis, sentiment
wink-sentiment
Accurate and fast sentiment scoring of phrases with #hashtags, emoticons :) & emojis 🎉
Stars: ✭ 51 (-84.55%)
Mutual labels:  sentiment-analysis, sentiment
Emotion and Polarity SO
An emotion classifier of text containing technical content from the SE domain
Stars: ✭ 74 (-77.58%)
Mutual labels:  sentiment-analysis, sentiment
Twitter Sentiment Analysis
This script can tell you the sentiments of people regarding to any events happening in the world by analyzing tweets related to that event
Stars: ✭ 94 (-71.52%)
Mutual labels:  sentiment-analysis, sentiment
NRC-Persian-Lexicon
NRC Word-Emotion Association Lexicon
Stars: ✭ 30 (-90.91%)
Mutual labels:  sentiment-analysis, sentiment
Pytreebank
😡😇 Stanford Sentiment Treebank loader in Python
Stars: ✭ 93 (-71.82%)
Mutual labels:  sentiment-analysis, sentiment
chronist
Long-term analysis of emotion, age, and sentiment using Lifeslice and text records.
Stars: ✭ 23 (-93.03%)
Mutual labels:  sentiment-analysis, sentiment
Text Analytics With Python
Learn how to process, classify, cluster, summarize, understand syntax, semantics and sentiment of text data with the power of Python! This repository contains code and datasets used in my book, "Text Analytics with Python" published by Apress/Springer.
Stars: ✭ 1,132 (+243.03%)
Mutual labels:  sentiment-analysis, sentiment
LSTM-sentiment-analysis
LSTM sentiment analysis. Please look at my another repo for SVM and Naive algorithem
Stars: ✭ 19 (-94.24%)
Mutual labels:  sentiment-analysis, sentiment
GroupDocs.Classification-for-.NET
GroupDocs.Classification-for-.NET samples and showcase (text and documents classification and sentiment analysis)
Stars: ✭ 38 (-88.48%)
Mutual labels:  sentiment-analysis, sentiment
billboard
🎤 Lyrics/associated NLP data for Billboard's Top 100, 1950-2015.
Stars: ✭ 53 (-83.94%)
Mutual labels:  sentiment-analysis, sentiment
Sentimentr
Dictionary based sentiment analysis that considers valence shifters
Stars: ✭ 325 (-1.52%)
Mutual labels:  sentiment-analysis, sentiment
Loritta
💁 A multipurpose, multilanguage, customizable, modular, and very cute bot for Discord using JDA! ~Making your server more awesome~
Stars: ✭ 253 (-23.33%)
Mutual labels:  moderation

troll

Language sentiment analysis and neural networks... for trolls.

Build Status

Troll is a tool for performing sentiment analysis (ie: "is this naughty or nice") on arbitrary blocks of text and associating it with a unique user. Using this data, combined with a rather naïve neural network and some training data, users can be indentified as "trolls".

Installation

Troll uses Redis for data storage. Once Redis is up and running, you can install Troll using NPM:

npm install troll

String Analysis

var troll   = require('troll');

troll.analyze('This is totally awesome!', 'user123', function (err, result) {
    console.log(result);    // 2.5
});

troll.analyze('This is lame.', 'user456', function (err, result) {
    console.log(result);    // -1.333
});

Training

Before attempting to classify a user, you'll need to train Troll. You can specify your own training data or use a basic set that is included. To load the included training set:

troll.train(function (err, result) {
    console.dir(result);    // { error: 0.0049931996067587685, iterations: 802 }
});

User Classification

Once trained, now you can classify:

troll.classify('user123', function (err, result) {
    console.dir(result);    // { total: 9, sum: 36, troll: 0.010294962292857838 }
});

The value returned for the troll key represents the probability of that user being a troll. In other words, a value of 0 would likely represent a particularly friendly user, while a value of 1 would be... uh, Ted Dziuba?


Modifing The Sentiment Engine

The underlying sentiment analysis module supports "injecting" additional key/value pairs. This is useful in certain situations where you may want to exclude or even blacklist certain words based on a particular use case. For example:

troll.inject({
    'stupid': -5,
    'lame': -5
});

troll.analyze('This is totally stupid and lame!', 'user123', function (err, result) {
    console.log(result);    // -5.833
});

Redis Connection Options

Troll uses your environment by looking at process.env for connection settings. If none are found, default Redis connection settings are used:

TROLL_HOST: null
TROLL_PORT: null
TROLL_PASS: null

Testing

npm test

Credits

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].