Tools

Visualization

Prepare and Visualize Mallet Topics

A Microsoft Excel spreadsheet with macros, to facilitate the visualization and analysis of Mallet topics. This spreadsheet accepts data from a topic model produced by Mallet. This sheet currently contains six macros that can be run by clicking the appropriate buttons.

Rated 0.0 out of 5.

Visualization

Easy Lineavis

Easy Linavis (ezlinavis) generates CSV files with network data from simple segmentations of literary texts that you can further visualise and analyse with Gephi or other tools. It provides more than 20 example files to make it easier to start.

Rated 0.0 out of 5.

Natural Language Processing

Tokenization and Extraction of Twitter Data

This notebook is part of a greater series of Juypter Notebook structured around Twitter Tweet analysis. This particular notebook will look at tokenization of extracting key features from a tweet text. This notebook also serves as one of the introductory notebook for TATR as tokenization and extraction are fundamental features for any analysis.

Rated 0.0 out of 5.

Analysis

Panda and CSV of Tweets

TATR: Panda and CSV of Tweets This notebook is part of a greater series of Juypter Notebook structured around Twitter Tweet analysis. This particular notebook will look at loading in a CSV (comma-separated values) file into a panda datastructure. Serving as one of the introductory coding notebook in the series, this notebook aims to teach and showcase how to load and save tweets into CSV files.

Rated 0.0 out of 5.

Visualization

Panda Dataframe Manipulation

TATR: This notebook is part of a greater series of Juypter Notebook structured around Twitter Tweet analysis. This particular notebook will look at Panda dataframe manipulation. It looks closely at panda index, groupby, and count features of panda. This notebook aims to teach these concepts and how they interact with csv.

Rated 0.0 out of 5.

Visualization

Graphing Twitter Data

TATR: Graphing This notebook is part of a greater series of Juypter Notebook structured around Twitter Tweet analysis. This particular notebook will look at graphing. From saving the resulting graph to organization. This notebook will provide the a framework that can be expanded to suit your needs.

Rated 0.0 out of 5.

Visualization

General Inquirer Category

TATR: This notebook is part of a greater series of Juypter Notebook structured around Twitter Tweet analysis. This particular notebook will look at categorizing text using the General Inquirer Categories released by Harvard (http://www.wjh.harvard.edu/~inquirer/spreadsheet_guide.htm). This notebook will showcase how to break down the General Inquirer Category into a dictionary and how it can be tailored to fit your needs.

Rated 0.0 out of 5.

Visualization

Finding Popular Hashtags

TATR: This notebook is part of a greater series of Juypter Notebook structured around Twitter Tweet analysis. This particular notebook will look at finding the most popular hashtag for a given date. This notebook will showcase two main features with the end goal of finding the most popular hashtag by date. The first feature is collapsing all the tokenized hashtag of a date into a larger set. The second feature is to save the "tokenized list" into a csv and load it back such that Panda dataframes can still treat this as a list. This notebook will also provide the a framework that can be expanded to suit your needs.

Rated 0.0 out of 5.

Annotating

Voronoi Diagram with Word Embedding

In this notebook, we will examine how to use word embedding and voronoi diagram to display the relationship between other words and a search term. Using A Tale of Two Cities by Charles Dickens as the example (acquired from Project Gutenberg), we will showcase how the program works as well as explain different modification and steps that can be taken in the future.

Rated 0.0 out of 5.

Visualization

Multiple Correspondence Analysis and Content Analysis

This notebook's aim is to showcase how to conduct Multiple Correspondence Analysis (MCA) on a corpus. In this notebook, we will be using a collection of novels by different authors i.e The Return of Sherlock Holmes by Arthur Conan Doyle, Lady Susan by Jane Austen, and A Christmas Carol by Charles Dickens taken from Project Gutenberg. First will gather and load in all the text. We clean them and break them down into tokens. We will categorize the tokens using General Inquirer Category taken from Harvard to conduct our analysis. From there we will conduct MCA on the results and plot the results on a scatter plot.

Rated 0.0 out of 5.