HOW DOES
DEEP WORK?

DEEP is an intelligent web-based platform that offers collaborative tools tailored for qualitative secondary data review. It combines the power of qualitative data analysis with AI-powered features to make the process as efficient and streamlined as possible. But what does this really mean?

Let’s dive a bit more into qualitative data analysis  and understand the AI power behind DEEP.

Image of a mac laptop featuring the DEEP platform on a blue wavy background
two text boxes of varying shades of blue on a light blue background

DEEP Qualitative Analysis

DEEP helps conduct more effective and efficient qualitative data analysis. In ever-changing and diverse contexts like humanitarian crises, there is a need to organize and break down reality into different categories. DEEP facilitates this division of information through customizable analytical frameworks.

With its multiple functionalities, DEEP provides analysts with a range of tools for collecting, processing, collating, visualizing, exporting, and analyzing data, ensuring a comprehensive understanding of complex scenarios.

simplify the PROCESS

DEEP facilitates the different steps involved in qualitative secondary data review

1
DATA COLLECTION
Chrome extension: Import pages and documents in DEEP directly while navigating on the web.

Various formats: DEEP supports a wide array of inputs to support the qualitative data review process (URLs, PDFs, Word files, Excel files, graphics).

Online vs local sources: Add documents to your projects from
a wide variety of sources such as online portals, cloud services or your local disk.

Connectors: Connect data platforms with your project in order to find sources easily.
2
DATA STRUCTURING
Analytical frameworks:
Create new projects to monitor, identify, and request to join and collaborate on existing projects; Clone, adapt or design your analysis framework and approach.

Tagging & Assessments registry:
Add own leads and sources;
Connect to multiple real-time data sources or feeds; Access structured and organized historical data.
3
DATA ANALYSIS
Analysis module:
Streamline your analytical process, making it more efficient and insightful; address critical aspects of your analysis by identifying information gaps and crafting analytical statements.

NLP Features
4
DATA VISUALIZATION & EXPORT
DEEP Dashboards: 
Get a visualization of all data gathered in your project;
Filter information.

Excel & Word exports:
Export all your data in either Excel or Word for sharing.

Reporting module:
Design, edit, and share web reports

DEEP AI

DEEP is the first humanitarian platform to integrate AI in the form of Natural Language Processing (NLP).  This field of study is focused on developing techniques and algorithms for processing and analyzing human language. It draws on knowledge from computer science, linguistics, and artificial intelligence, among other areas. NLP is concerned with tasks such as text classification, sentiment analysis, language translation, speech recognition, and text summarization, among others.

In DEEP we use this technology to support the humanitarian sector with classification and categorization for analysis tasks and report generation for crises. It is embedded in the platform to quickly categorize, extract, summarize, and analyze texts to generate reports in a more efficient manner. DEEP has practical applications of Artificial intelligence making it the pioneer in bringing NLP to the humanitarian and development sectors.

Two speech bubbles in different shades of blue on a light blue backgroun

FEATURES

Topic Modeling
Using it to identify the topics present in a large corpus of text data and for analyzing large volumes of text data and identifying meaningful patterns and insights.
Blue location icon
Automatic Geo-tagging
Optimizing a model that extracts geographic information from the text.
Automatic Summarization
Automatizing the summarization step for creating reports using annotated data.
Assisted Tagging
A multi-label classification model tailored for common humanitarian analysis frameworks and trained on DEEP data with direct access in DEEP and a pluggable interface for other applications.
Entry Extraction
This model selects a subset of passages that contain relevant information from the given document; these entries do not necessarily follow the common units of text such as sentence and paragraph and can appear in various lengths.
Blue four point star
Automatic Analysis
DEEP supports analysts in automatically creating reports and analysis within just a few clicks.

FAQ

How does the conversation on humanitarian AI ethics apply to NLP?

We identified some risks such as potential harm coming to those affected by the tools, for example beneficiaries of humanitarian aid, risks to human rights of beneficiaries, discriminatory or stereotypical treatment of certain groups in the tool, threats to the safety of certain groups, impact on the humanity, neutrality, impartiality and independence of humanitarian organisations and cybersecurity risks.  In our attempt to create technology with the highest ethical considerations, we make sure we work to mitigate those risks in research and practice. We start then our first application as follows:

As part of the humanitarian imperatives of neutrality and impartiality, it is important to be aware and to reduce the societal biases and stereotypes encoded in the models. Part of our research is focused on defining, measuring and mitigating the possible societal and harmful biases reflected in the classification models, while maintaining the high accuracy and performance of the models.

Is the data I upload to DEEP secure, and who has access to it?

DEEP prioritizes data security and privacy. All data uploaded to the platform is encrypted both in transit and at rest. You control who can access your data by setting permissions within your workspace. Only authorized users—those you explicitly invite—can view or edit the information. Additionally, DEEP complies with data protection regulations to ensure your data is handled responsibly.

Does DEEP support multiple languages?

Currently DEEP is only available in English. However, we have an open-source platform that means that it can be adapted for other languages and we have it on the technical roadmap.

Who can use DEEP, and do I need specific technical skills to get started?

DEEP is designed for anyone involved in humanitarian analysis, including data analysts, researchers, and decision-makers. You don’t need advanced technical skills to get started, however you will need an understanding of qualitative analysis.  DEEP  offers training materials and support to help new users quickly become proficient. If you need additional support, please reach out to support@thedeep.io

How can I use DEEP to collaborate with other analysts in different organization?

DEEP allows for seamless collaboration through shared workspaces. You can invite team members to join a project, assign specific roles, and work together on the same datasets in real time. The platform tracks changes and provides an activity log, making it easy to coordinate efforts and ensure consistency across the analysis being conducted.

How often is DEEP updated, and what new features can we expect?

DEEP is regularly updated to improve functionality and user experience. Updates typically include new features, performance enhancements, and bug fixes. The development team actively gathers feedback from users to prioritize improvements.  Keep an eye on the DEEP website or community announcements for the latest updates.

WHAT'S NEW IN DEEP?

LATEST FEATURES

Reporting Module
Allows users to design, edit and share a web report containing DEEP qualitative analysis and visualizations, organized based on the analysis framework.
Find out moreGitHub
Auto Extraction and Classification
Leveraging automatic text extraction and classification to elevate users' experience to enable faster and more efficient secondary analysis.
Find out moreGitHub
Automation of the Analysis Module
Employing Natural Language Processing to auto-fill fields in DEEP, such as Information Gaps, Analytical Statement and My Analysis.
Find out moreGitHub

TECHNICAL ROADMAP

Latest Initiative:
JAWS

The Joint Analysis Workspace (JAWS) will use advanced technologies to integrate qualitative and quantitative data and elicit expert judgement. JAWS is designed to be an agile platform, supporting various use cases such as needs and situation analysis, research, learning, and outcome monitoring.

JAWS logo where the A is a shark fin