-
Notifications
You must be signed in to change notification settings - Fork 604
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Updating figures & descriptions for Ch 8 #23
- Loading branch information
Showing
1 changed file
with
39 additions
and
11 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,25 +1,53 @@ | ||
|
|
||
| # Social Media | ||
|
|
||
| Set of notebooks associated with Chapter 8 of the book | ||
| ## 🔖 Outline | ||
|
|
||
| 1. **[Create a wordcloud](https://github.com/practical-nlp/practical-nlp/blob/master/Ch8/01_WordCloud.ipynb)**: How to create a wordcloud. This is often used to get a quick sense of given text corpus at hand. | ||
| To be added | ||
|
|
||
| 2. **[Effect of different tokenizers on Social Media Text Data](https://github.com/practical-nlp/practical-nlp/blob/master/Ch8/02_DifferentTokenizers.ipynb)** : Here we show how different tokenizers can give different output for the same input text. When dealing to text data from social platforms this can have huge bearing on the performance of the task. Here, we will be working with 5 different tokenizers, namely: | ||
|
|
||
| * [word_tokenize from NLTK](https://www.nltk.org/api/nltk.tokenize.html) | ||
| * [TweetTokenizer from NLTK](https://www.nltk.org/api/nltk.tokenize.html) | ||
| * [Twikenizer](https://pypi.org/project/twikenizer/) | ||
| * [Twokenizer by ARK@CMU](http://www.cs.cmu.edu/~ark/TweetNLP/) | ||
| * [twokenize](https://github.com/leondz/twokenize) | ||
|
|
||
| ## 🗒️ Notebooks | ||
|
|
||
| Set of notebooks associated with the chapter. | ||
|
|
||
|
|
||
| 1. **[Create a wordcloud](https://github.com/practical-nlp/practical-nlp/blob/master/Ch8/01_WordCloud.ipynb)**: How to create a word cloud. This is often used to get a quick sense of given text corpus at hand. | ||
|
|
||
| 2. **[Effect of different tokenizers on Social Media Text Data](https://github.com/practical-nlp/practical-nlp/blob/master/Ch8/02_DifferentTokenizers.ipynb)** : Here we show how different tokenizers can give different output for the same input text. When dealing with text data from social platforms this can have a huge bearing on the performance of the task. Here, we will be working with 5 different tokenizers, namely: | ||
|
|
||
| * [word_tokenize from NLTK](https://www.nltk.org/api/nltk.tokenize.html) | ||
| * [TweetTokenizer from NLTK](https://www.nltk.org/api/nltk.tokenize.html) | ||
| * [Twikenizer](https://pypi.org/project/twikenizer/) | ||
| * [Twokenizer by ARK@CMU](http://www.cs.cmu.edu/~ark/TweetNLP/) | ||
| * [twokenize](https://github.com/leondz/twokenize) | ||
|
|
||
|
|
||
| 3. **[Trending topics](https://github.com/practical-nlp/practical-nlp/blob/master/Ch8/03_TrendingTopics.ipynb)**: Find trending topics on Twitter using tweepy | ||
|
|
||
| 4. **[Sentiment Analysis](https://github.com/practical-nlp/practical-nlp/blob/master/Ch8/04_Sentiment_Analysis_Textblob.ipynb)**: Basic sentiment analysis using TextBlob | ||
|
|
||
| 5. **[Preprocessing Social Media Text Data](https://github.com/practical-nlp/practical-nlp/blob/master/Ch8/O5_smtd_preprocessing.py)**: Common functions involved in pre-processing pipeline for Social Media Text Data. | ||
| 5. **[Preprocessing Social Media Text Data](https://github.com/practical-nlp/practical-nlp/blob/master/Ch8/O5_smtd_preprocessing.py)**: Common functions involved in the pre-processing pipeline for Social Media Text Data. | ||
|
|
||
| 6. **[Text representation of Social Media Text Data](https://github.com/practical-nlp/practical-nlp/blob/master/Ch8/06_SMTD_embeddings.ipynb)**: How to use embeddings to represent Social Media Text Data | ||
|
|
||
| 7. **Sentiment Analysis**: Here we use the preprocessing and representation steps learnt before to build a better classifier. | ||
| 7. **Sentiment Analysis**: Here we use the preprocessing and representation steps learnt before to build a better classifier. | ||
|
|
||
|
|
||
| ## 🖼️ Figures | ||
|
|
||
| Color figures as requested by the readers. | ||
|
|
||
|  | ||
|  | ||
|  | ||
|  | ||
|  | ||
|  | ||
|  | ||
|  | ||
|  | ||
|  | ||
|  | ||
|  | ||
|  | ||
|  |