Gephi meet-up #3 in Berlin

user-group_smallText Network Analysis with Gephi by Dmitry Paranyushkin / Nodus Labs

In this workshop we will demonstrate a novel method for text network analysis using Gephi graph visualization software. Unlike other topic modelling methods (latent semantic network analysis, LDA) our approach takes into account the structural properties of text network in order to identify the clusters for meaning circulation and the most influential concepts within the text. You will learn how to create graph network representations of texts and perform their comparative quantitive and qualitative analysis. The method can be especially useful for quick text summarization and group sentiment profiling.

What It Can Be Used For:

– Identifying the most influential concepts and topics within a text.
– Comparing different texts together, especially what strategy a text uses to “push” a certain agenda.
– Group sentiment analysis: find the terms that unite any group together
– Quick text summary and overview (can be especially useful for studying or law text)

If you’d like to participate you can send us a short text (200 to 300 words) to info at noduslabs dot com describing your interests and current occupations. We will create text graphs both for participants and the whole group and see how they relate to one another (see the image attached). This may also be useful for you to meet other like-minded individuals at betahaus or find the people who could complement your cognitive map with their knowledge.

To sign up:

Date: 7th of December, Wednesday, 18.00 to 20.00
Place: betahaus, 19-20 Prinzessinnenstr (U8: Moritzplatz), 4th floor Arena hall

We highly recommend you to bring your laptop with you and pre-install Gephi graph visualization software on your computer (works on Mac, PC, Linux).

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s