Skip to main content

Sentiment analysis for paragraph or sentence

Project description

Sentiment_analysis (감성 분석)

일기 및 일상 평문 텍스트에서, 글쓴이의 감정을 유추하기 위해서 만들어진 라이브러리입니다. 감성 분석을 위해서, Keras 및 nltk가 사용되었습니다. 또한, 텍스트의 길이에 따라서 문장을 요약하고 이에 대한 감성을 각각 분석을 하기 위해 Lexrank 알고리즘이 사용되었습니다.

해당 라이브러리는 감성을 다음 6가지의 종류로 분류합니다. (우울함, 분노, 불안, 고통, 당황, 행복)

※ 주의)

이 라이브러리는 한국어와 영어를 제외한 다른 언어를 지원하지 않습니다. 추후, 일어, 중어 및 다른 언어들에 대한 지원을 할 예정입니다.

This library is made for analyzing sentiment from a single sentence or paragraph. It uses Keras and nltk. In addition, It also uses LexRank algorithm to summarize a paragraph.

It classifies sentiment as 6 emotions (Depression, Anger, Anxiety, Agony, Embarrassed, Happiness)

※ Caution)

This library does not support other languages except English and Korean yet. However, we have a plan to support other languages includes Japanese, Chinese, and etc.

Getting agony score won't work, if detected language is English. Be careful.

Installation

pip install sentiment-analysis

Usage

from sentiment import SentimentAnalysis
sentiment_analysis = SentimentAnalysis(want_to_analyze_sentence_or_paragraph)
sentiment_analysis.analyze() # It initializes analysis progress

sadness_score = sentiment_analysis.get_sadness_score() # get depression score.
anger_score = sentiment_analysis.get_anger_score() # get anger score.
anxiety_score = sentiment_analysis.get_anxiety_score() # get anxiety score.
agony_score = sentiment_analysis.get_agony_score() # get agony score.
embarrassed_score = sentiment_analysis.get_embarrassed_score() # get embarrassed score.
happiness_score = sentiment_analysis.get_happiness_score() # get happiness score.

total_score = sentiment_analysis.get_total_score() # get all scores as list type.

positive_score = sentiment_analysis.get_positive_score() # get positive scores
negative_score = sentiment_analysis.get_negative_score() # get negative scores

Reference)

  1. https://github.com/theeluwin/lexrankr (Korean Lexrank)
  2. https://www.kaggle.com/c/sa-emotions/data# (English data supported)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

sentiment_analysis-0.1.4-py3-none-any.whl (5.0 kB view details)

Uploaded Python 3

File details

Details for the file sentiment_analysis-0.1.4-py3-none-any.whl.

File metadata

  • Download URL: sentiment_analysis-0.1.4-py3-none-any.whl
  • Upload date:
  • Size: 5.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.0.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.4.0 requests-toolbelt/0.9.1 tqdm/4.36.1 CPython/3.7.4

File hashes

Hashes for sentiment_analysis-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 6e9682d5b7ee51116db5efc350f6386551cbcaf9b05e0b4096e904ce0aa0cc78
MD5 24ca7cebe8843fbb6597c8b312e6563b
BLAKE2b-256 edd41d0d87203f78320449e05d5e0ee2f627e49b5815b5f8f7ef417fe82141e6

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page