Data

Tools

Indexes

Applications

Experiments

Open Source Science

sentimentanalysis

SUTD Machine Learning Project

https://github.com/yingjieqiao/sentimentanalysis

Science Score: 57.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 2 DOI reference(s) in README
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.9%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

SUTD Machine Learning Project

Basic Info
  • Host: GitHub
  • Owner: YingjieQiao
  • Language: Python
  • Default Branch: master
  • Homepage:
  • Size: 1020 KB
Statistics
  • Stars: 0
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 4 years ago · Last pushed about 4 years ago
Metadata Files
Readme Citation

README.md

50.007 Machine Learning Project

| Team Member | Student ID | | :-----------: | :--------: | | Qiao Yingjie | 1004514 | | Zhang Peiyuan | 1004539 | | Huang He | 1004561 |

Introduction

In the repository, we present a pure python based implementation of the hidden markov model (HMM) and second-order hidden markov model for the task of simple sentiment analysis.

Please refer to our Report for implementation details and results.

Dependencies:

  • Python 3.6+ Only (no external libraries required)

Demo

Run all trainings and evaluations for Part 1,2,3,4 at one go:

bash ./run_all

Part 1

Relevant code section:

To run the code

bash python3 hmm.py --train "ES/train" --test "ES/dev.in" --naive python3 hmm.py --train "RU/train" --test "RU/dev.in" --naive

Part 2 & 3

Relevant code section:

  • Function that computes the transition probability: hmm.py Line 69-108
  • We use log-likelihood to compute the probability of emission and transition to avoid underflow: hmm.py Line 100
  • We also introduce a smoothing factor which is a small constant that will be used to estimate close-to-zero probability to avoid undefined log-likelihood probabilities. hmm.py Line 100
  • Top-k Viterbi algorithm: hmm.py Line 186-260

To run the code

bash python3 hmm.py --train "ES/train" --test "ES/dev.in" --top-k "5" python3 hmm.py --train "RU/train" --test "RU/dev.in" --top-k "5"

Part 4: RNN & 2nd Order HMM

We implement the second order HMM in secondorderhmm.py

To run the code

bash python3 second_order_hmm.py --train "ES/train" --test "ES/dev.in" python3 second_order_hmm.py --train "RU/train" --test "RU/dev.in"

Acknowledgement

We refer to the following resources when implementing this project:

Owner

  • Name: Yingjie Qiao
  • Login: YingjieQiao
  • Kind: user
  • Location: Singapore
  • Company: @ByteDance

Do solid works, build exciting things, and make an impact.

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this repository, please cite it as below."
authors:
    - family-names: "Huang"
      given-names: "He"
      orcid: "https://orcid.org/0000-0002-9217-4977"
      affiliation: "Singapore University of Technology and Design"
    - family-names: "Zhang"
      given-names: "Peiyuan"
      affiliation: "Singapore University of Technology and Design"
    - family-names: "Qiao"
      given-names: "Yingjie"
      affiliation: "Singapore University of Technology and Design"
title: "Pure Python Hidden Markov Model Implementation for Sentiment Analysis"
version: 0.0.1
date-released: 2021-12-13
url: "https://github.com/YingjieQiao/SentimentAnalysis"

GitHub Events

Total
Last Year

Issues and Pull Requests

Last synced: 12 months ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels