Use case SERP

Skip to main content

Username

Password

Shibboleth Login Login as Guest

Forgotten your username or password?

Home Contact

About

The #dariahTeach Project
The IGNITE Project

Testimonials

Search

Use case SERP

◄ Datasets show page overview

Jump to...

Compound mode ►

Skip Course Custom Menu

Course Custom Menu

What is Historical Newspapers Analysis and Why Bother?

Unit I: Introduction to historical newspaper and the NewsEye platform

1.1 Introduction to Historical Newspaper Analysis and Digitisation

1.1.1 Historical newspapers: an infinite source of data
1.1.2 What is NewsEye?
1.1.3 From paper to digital
1.1.4 From data to information: overview

original newspaper vs OCR text

Unit II: Searching with the NewsEye Platform

2.1. Presentation of the NewsEye Platform

2.1.1. The search page
2.1.2. The search result page
2.1.3. The document show page
2.1.4. The datasets pages
2.1.5. Creating a dataset

2.2. Understanding how the platform works

2.2.1. Demonstration of blackboxes
2.2.2. Indexing textual content
2.2.3. Opening the blackbox : the ranking problem

Results page overview

Datasets show page overview

Exemple of a processed text

Quality of OCR extracted text

Example of XML file generated by OCR process

Matrix of our collection

Unit III: Information extraction and document understanding

3.1 Document Understanding and Information Extract : Overview and Programming Basics

3.1.1 Overview
3.1.2 Information Extraction History
3.1.3 Text Pre-processing : Programming Basics

3.2 Natural Language Processing (NLP) programming basics

3.2.1 Natural Language Processing (NLP) basics
3.2.2 Natural Language Processing (NLP) advanced

3.3 Extracting information : Named Entity Recognition (NER)

3.3.1 What are named entities ?
3.3.2. Why are named entities important?
3.3.3 Named Entity Recognition with Python

Stopwords interactive activity

NER interactive activity

Unit IV: Discover and use a corpus of historical newspapers

4.1 Approaches for analysing newspaper collection

4.1.1 Reading the corpus
4.1.2 Exploring data using wordclouds
4.1.3 Focusing on meaningful: adding POS tagging
4.1.4 Extracting named entities
4.1.5 Mapping locations on a map

Spanish Flu dataset

Skip Navigation

Navigation

Home
- Site pages
- Courses
  - Digital Research on European Historical Newspapers...

Back

Guest (Log in)