Main Applications of Natural Language Processing(NLP) — 3

Today, we’d like to talk about Emotional analysis.

Emotional analysis, also known as opinion mining, tendentiousness analysis. Simply speaking, it is the process of analyzing, concluding, and reasoning on subjective content. By judging the emotional orientation in the information, it supports word-of-mouth analysis, topic monitoring, public opinion analysis, etc.

The following is an example of a multi-category labeling loop:

1. Emotion Classification

Emotions can be divided into 3 categories, 11 categories, and 25 subcategories:

2. Labeling Process

Given a short conversation, the labeler needs to figure out the emotion in each sentence, and classify it into 25 categories. If the emotion belongs to one sub-class, label 1, if not, label 0.

3. Output

Dialogue Contents A:

John, congratulations on having passed the examination, you are excellent.

Examples of annotation:

Dialogue Contents B:

Thank you very much for inviting me to the diner. You are very generous!

Examples of annotation:

Dialogue Contents C:

I agree with you. You are lucky, but you have prepared so hard for the game. You certainly deserve it.

Examples of annotation:

Dialogue Contents D:

Thank you for caring about us. I really appreciate it. I am looking forward to reconnecting with you.

Examples of annotation:

Bytebridge: a Human-powered and ML-powered Data Labeling Tooling Platform, provides Content Relevance Service

ByteBridge is a data collection and labeling platform with robust tools and real-time workflow management.

We provide different types of NLP in E-commerce, Retail, Search engines, Social Media, etc. Our service includes Voice Classification, Sentiment Analysis, Text recognition/Classification.