How to build a Social Computer SS2023

Background

Computers, mobile phones, and wearables are part of our daily lives. Its user interfaces are designed to interact with facts, e.g. health parameters, documents, etc. – which is sufficient for some applications. But what if a computer system would understand users like human do and adapt to the individual social situation in order to establish a social human-like interaction? Such concepts are highly relevant to social training systems, e.g. virtual job interview training and work-life-balance systems. This interdisciplinary seminar in Psychology and Artificial Intelligence investigates the question „How to make computers social?“. What is social? What concepts, theories help to define being social? How do humans socially communicate? How can this be transferred into a computer model? What is technically feasible? How can this be exploited for social training systems? Relevant concepts and theories will be presented, discussed, and transferred into computer models. Three prototypical interactive social computer applications will be created as proof of concept. Students of Psychology and Computer Science will work together designing, discussing, implementing, and creating an evaluation plan for each application.

Goal

In the seminar mixed student teams (computer science and psychology) will work on projects to design, implement and evaluate an affective application. There should be a lively exchange between the two disciplines to in order to create a well thought-out system.

Organisational information

 

General

The seminar will be in Turing II, DFKI D3.4
(You are very welcome to ask at the front desk for instructions on getting there)

Tuesdays between 14:00 and 16:00. 

Don’t miss the general information and requirements. 

Participation

In total, maximal 18 students can participate in the seminar. 9 psychology students and 9 computer science students. Psychology students have the usual process for getting into seminars by registering in LSF. Computer Science students use the Seminar Assignment website by SIC. 

Students of psychology obtain 4 ECTS for attending the seminar. 

Students of computer science obtain 7 ECTS for attending the seminar. As usual for computer science, they will be graded. The grading includes the participation during the seminar, implementation and evaluation of the final project. 

Structure

Besides the kickoff meeting, we will have weekly meetings (all participants, 90min) in which the seminar groups are presenting theirs projects. We will discuss your ideas, your project plans, concerns and localize problem solutions.

By end of June, each group will get 45 mins to present their implemented project in details. 

Between the weekly meetings, you are expected to have individual group meetings to plan your progress presentations. Individual group meetings are meetings of the whole project team in a project team channel. As a team, you will find the best way to make sure you are ready to present your progress and that every member is contributing. 

Schedule

#	Date	Seminar Goals	What to do?
1	18.04	Kick off	Be present at Turing II, DFKI D3.2 Look at General Material I
2	25.04	General Material II	Do the assigned readings
3	02.05	Project Topic Readings	Submit your topic preference (Excel Sheet)  Start looking at the assigned readings and propose a focus for your project. What are the open questions for you? (3-4 slides) Register in LSF!
4	09.05	Pitch your idea	Read the assigned project readings  Prepare project title and discussion of basic literature
5	16.05	Pitch your idea	Discuss the idea – the basic research question for SoSci and CS (10-15 mins per group)
6	23.05	Identify final tools	Discuss conceptualisation (tools, instruments, materials…)
7	30.05	Finalize your idea	Discuss operationalisation
8	06.06	Presentation I	Presentation I – Idea, conceptualization and operationalisation (15 mins per group)
9	06.06	Progress	Propose a realisation of your idea
10	13.06	Progress	Discuss the realisation and validation plan of your idea
11	20.06	Mid-presentation	Realization and validation plan presentation (45 minutes)
12	27.06	Mid-presentation	Realization and validation plan presentation (45 minutes)
13	04.07	Mid-presentation	Realization and validation plan presentation (45 minutes)
14	11.07	Progress	Discuss validation/results of the project
15	18.07	Final Presentation	Executive presentation with limitations, conclusion, and future research/ Plan

Projects

To be announced by the 2nd week.

Material

Slides/Media

How to give a great research talk (Youtube, Simon Peyton Jones, Microsoft Research Cambridge)

General Literature

Barrett, L. F., Adolphs, R., Marsella, S., Martinez, A. M., & Pollak, S. D. (2019). Emotional Expressions Reconsidered: Challenges to Inferring Emotion From Human Facial Movements. Psychological Science in the Public Interest, 20(1), 1–68. https://doi.org/10.1177/1529100619832930

Barrett, L. F. (2019) Keynote at 8th International Conference on Affective Computing and Intelligent Interaction (ACII)

Ekman, P. (2017). The Ekman’s Atlas of Emotions. 

Schneeberger, T., Gebhard, P., Baur, T., & André, E. (2019). PARLEY: A transparent virtual social agent training interface. International Conference on Intelligent User Interfaces, Proceedings IUI, 35–36. PARLEY

Wagner, J., Lingenfelser, F.,  Baur, T., Damian, I., Kistler, F., André, E. (2013). The Social Signal Interpretation (SSI) Framework: Multimodal Signal Processing and Recognition in Real-Time. In Proceedings of the 21st ACM international conference on Multimedia. ACM, 831–834. SSI framework 

Gebhard, Patrick & Schneeberger, Tanja & Baur, Tobias & Andre, Elisabeth. (2018). MARSSI: Model of Appraisal, Regulation, and Social Signal Interpretation. MARSSI Model of Appraisal, Regulation, and Social Signal Interpretation.

Software

VisualSceneMaker, an authoring tool for Virtual Characters.

ALMA, a computational model of affect that implements the appraisal theory of emotions from the psychologists Ortony, Clore, and Collins.

OpenSSI, a framework for analysing social signals in realtime.

YALLAH, Yet another low‐level agent handler.

 

Contact

Alexandra (Tutor, Psychology, alexandra.alles@dfki.de),

Chirag (tutor, Computer science, chirag.bhuvaneshwara@dfki.de),

Mina (tutor, Computer science, mina.ameli@dfki.de),

Manuel (tutor, Computer science, Manuel.anglet@dfki.de), 

Lara (tutor, EduTech, lara.chehayeb@dfki.de),   

Dimitra (seminar advisor, EduTech, dimitra.tsovaltzi@mx.uni-saarland.de),   

Fabrizio (seminar advisor, Computer science, fabrizio.nunnari@dfki.de)  

Patrick (seminar advisor, Computer science, gebhard@dfki.de).