Back to Education
Deep Learning Specialization · Sequence Models

Emojify: Emoji Prediction from Text

A sentence-to-emoji classifier that starts with averaged GloVe vectors and then improves the representation with an LSTM sequence model.

GloVe embeddingsSentence classificationLSTMWord-order modelingSoftmax emoji prediction
GitHub

What this project is about

Emojify compares a simple average of word vectors against an LSTM-based sequence model. It shows how embeddings capture meaning and how sequence models can preserve order.

Implementation focus

The project highlighted a common NLP lesson: semantic vectors help even with small datasets, but word order and negation often require sequence-aware architectures.

Key results and artifacts

  • Classes: ❤️ ⚾ 😄 😞 🍴
  • Training set: 127 examples; test set: 56 examples
  • V1 test accuracy: ~91.07%; V2 test accuracy: ~83.93%

What I learned

This project showed why word order matters: averaging embeddings can understand meaning, but sequence models handle negation and context better.

Milestone deep dive

What this project proves in my learning path.

A sentence-to-emoji classifier that starts with averaged GloVe vectors and then improves the representation with an LSTM sequence model. The milestone is included because it shows a complete learning unit: a problem, a data representation, an implementation path, measurable outputs, and a lesson that later connects to larger AI systems.

Input layerordered sequences of text, audio, dates, or musical events
Model layerrecurrent or attention-based sequence model
Evaluation layertests, metrics, plots, or qualitative output
Artifact layerclassification, generation, alignment, or trigger probabilities
Problem framing

What I was trying to solve

This page is not just a lab description. It explains how I transformed the assignment idea into an engineering story: what the model receives, what it optimizes, what output it should produce, and how the result can be inspected.

Implementation

What I coded or assembled

The implementation focus was the mechanism behind the result: functions, model blocks, training logic, preprocessing, evaluation, and the small technical details that make the notebook work rather than only look correct.

Concepts

Core concepts

GloVe embeddingsSentence classificationLSTMWord-order modelingSoftmax emoji prediction

These tags show the technical ideas this milestone added to my toolkit.

Learning result

What changed after it

This project showed why word order matters: averaging embeddings can understand meaning, but sequence models handle negation and context better.

Important outputs and evidence

  • Classes: ❤️ ⚾ 😄 😞 🍴
  • Training set: 127 examples; test set: 56 examples
  • V1 test accuracy: ~91.07%; V2 test accuracy: ~83.93%

How I would explain it in an interview

I would describe this milestone by starting from the data representation, then explain the model or algorithm, then show what was measured. The important part is not only the final number; it is the ability to reason about why the method works, what assumptions it makes, and what limitations should be improved next.