EMAS2019_paper_5.pdf :  From Goals to Organisations: automated organisation generator for MAS? Cleber Jo
EMAS2019_paper_8.pdf :  Jacamo-web is on the fly: an interactive Multi-Agent System IDE? Cleber Jorge Am
EMAS2019_paper_18.pdf :  SAT for Epistemic Logic using Belief Bases Fabián Romero1 and Emiliano Lorini1 
EMAS2019_paper_21.pdf :  JS-son - A Minimal JavaScript BDI Agent Library Timotheus Kampik and Juan Carlos
EMAS2019_paper_22.pdf :  An Architecture for Integrating BDI Agents with a Simulation Environment Alan Da
EMAS2019_paper_23.pdf :  Using MATSim as a Component in Dynamic Agent-Based Micro-Simulations Dhirendra S
EMAS2019_paper_24.pdf :  Plan Library Reconfigurability in BDI Agents? Rafael C. Cardoso, Louise A. Denni
EMAS2019_paper_25.pdf :  Incorporating social practices in BDI agent systems Stephen Cranefield1 and Fran
EMAS2019_paper_26.pdf :  Accountability and Agents for Engineering Business Processes Matteo Baldoni1, Cr
EMAS2019_paper_27.pdf :  The “Why did you do that?” Button: Answering Why-questions for end users of Robo
EMAS2019_paper_28.pdf :  Concurrency and Asynchrony in Protocol Languages Amit K. Chopra1, Samuel H. Chri
EMAS2019_paper_29.pdf :  On Enactability of Agent Interaction Protocols: Towards a Unified Approach Angel
EMAS2019_paper_30.pdf :  Who’s that? - Modelling Social Situations for Behaviour Support Agents? Ilir Kol
EMAS2019_paper_31.pdf :  What Does It Take to Create Social Awareness for Support Agents?? Ilir Kola1, Ca
EMAS2019_paper_32.pdf :  An Introduction to Engineering Multiagent Industrial Symbiosis Systems: Potentia
EMAS2019_paper_33.pdf :  From Programming Agents to Educating Agents – A Jason-based Framework for Integr
EMAS2019_paper_34.pdf :  Hercule: Reasoning about Norms over Unstructured Events Samuel H. Christie V1, A
EMAS2019_paper_35.pdf :  Agents are More Complex than Other Software: An Empirical Investigation Alon T. 

How it works?

It downloads the accepted papers available in EMAS 2019 page. Each paper in PDF is converted to a plain text using Apache Tika. Then using Google Universal Sentence Encoder they are vectorized. These vectors are compared creating correlations. The correlations vary from 0 to 100% of similarity. Those values are presented in an Altair correlation matrix.

What else it can do?

I use it to find correlations across many papers and books I use in my researches. Since I use Mendeley, all of them are in a plain folder. The project called text-correlation retrieves all documents from a local folder creating a correlation matrix n x n in a .csv file. It is better for larger number of documents and suitable to open in a spreadsheet processor.


Developed by Cleber Jorge Amaral, acknowledging it is highly inspired by a work presented by Aladdin Shamoug