=Paper=
{{Paper
|id=Vol-2787/paper7
|storemode=property
|title=Affective Games Provide Controlable Context. Proposal of an Experimental Framework
|pdfUrl=https://ceur-ws.org/Vol-2787/paper7.pdf
|volume=Vol-2787
|authors=Laura Żuchowska,Krzysztof Kutt,Krzysztof Geleta,Szymon Bobek,Grzegorz J. Nalepa
|dblpUrl=https://dblp.org/rec/conf/ecai/ZuchowskaKGBN20
}}
==Affective Games Provide Controlable Context. Proposal of an Experimental Framework==
https://ceur-ws.org/Vol-2787/paper7.pdf
Eleventh International Workshop Modelling and Reasoning in Context (MRC) @ECAI 2020 45
Affective Games Provide Controlable Context.
Proposal of an Experimental Framework
Laura Żuchowska and Krzysztof Kutt and Krzysztof Geleta and Szymon Bobek and Grzegorz J. Nalepa1
Abstract. We propose an experimental framework for Affective in 4. Furthermore, we realized that in order to provide flexibility of
Computing based of video games. We developed a set of specially such experiments, we should have a framework supporting the re-
designed mini-games, based of carefully selected game mechanics, configuration of such experiments for a range of game levels. We de-
to evoke emotions of participants of a larger experiment. We believe, veloped a prototype of such a framework, as described in Section 5.
that games provide a controllable yet overall ecological environment A short comparison with other solutions is provided in Section 6. In
for studying emotions. We discuss how we used our mini-games as Section 7 we describe the evaluation of our work. We conclude the
an important counterpart of classical visual and auditory stimuli. Fur- paper in Section 8.
thermore, we present a software tool supporting the execution and
evaluation of experiments of this kind.
2 MOTIVATION
1 INTRODUCTION Research on emotions requires, on the one hand, a controllable ex-
perimental environment to evoke and detect and emotions, on the
Emotions constitute an important context for interpretation of human
other, natural conditions for experiments in order to minimize a pos-
behavior. Affective computing (AfC) is a field of study devoted to the
sible discomfort for the participants. Video games seem to be a good
computer-based analysis, modeling and synthesis of emotions [14].
trade-off between these two extreme requirements. Games allow to
In our work in this area, we focus on the use of wearable and mobile
control the appearing stimuli and log everything that happened, espe-
devices to support the acquisition and interpretation of bodily signals
cially the reaction times, Moreover, the environment is rich in stimuli
in order to the detect changes of affective states and possibly recog-
and allows for user interaction with objects, including emotionally
nize the corresponding emotional states of subjects. We believe, that
related interaction framed in the so-called Affective Loop [12].
the context-aware systems paradigm considered in computer science,
“Regular” games, available on the market, do not meet the require-
should take into the account the affective dimension [11]. Further-
ments of the experimental environment. First of all, they provide a
more, the computer models should be personalized, i.e. take into the
(too) rich environment in which the player may do (too) many things.
account individual differences of human behavior, as well as person-
In such an environment, a very large sample size is needed to get the
ality traits [8].
right statistical power to draw conclusions, which makes experiments
One of the principal challenges in the AfC experiments is the ac-
difficult to conduct. Also, the use of machine learning methods will
tual process to evoke individual emotions for the training and cali-
not be trivial, as there are many variables in such case, some of which
bration of computer models. In the psychological literature, some of
will only be disruptive noise. Secondly, “regular” games do not allow
the typical experimental procedures assume the use of standardized
for the evaluation of emotions too often. The player is constantly en-
visual and auditory stimuli that are supposed to evoke the specific
gaged in the game and interrupting it to complete the questionnaire
emotions. From our perspective, such an approach is not sufficient as
will reduce the immersion of the game.
the experimental situation very often does not seem natural to the par-
These issues have been observed in our previous experiments [11]
ticipant, furthermore it is not personalized. To tackle this challenge,
including the BIRAFFE1 experiment [8]. To address them, a set of
in our work we employ computer games as the source of specific,
mini games, with restricted experimental conditions, was created.
rich, natural, yet controllable context to evoke emotions [12].
Each of them is built up on a very limited set of stimuli, with the
In this paper we present an experimental setup using affective
aim of evoking a limited set of emotional reactions. The following
games to evoke emotions of the participants. The principal contri-
sections describe an experiment called BIRAFFE2 (see Section 3) in
butions include: the design of original video games aimed at AfC ex-
which three such games were used (see Section 4).
periments, a framework for configuration of experiments using such
The BIRAFFE2 experiment has led to observation of further issues
games, putting these two in the context of the BIRAFFE experiments
that need to be addressed when conducting game experiments. In
we conducted.
particular, attention has been drawn to the fact that all mini games
The rest of the paper is organized as follows: In Section 2 we dis-
should generate event logs in a uniform format to avoid additional
cuss the detailed motivation of our work. Then in Section 3 we de-
pre-processing steps when analysing the collected data. It is equally
scribe an experiment in AfC we conducted to acquire data on the
important to implement questionnaires directly in the games, at the
individual affective reactions. In this experiment we used a set of af-
end of each mini game. Filling out the questionnaires at the end of the
fective games we specifically developed for this task, as described
gaming session makes the impressions fuzzy and the self-description
1 Jagiellonian University, Poland, email: krzysztof.kutt@uj.edu.pl, szy- may not be accurate enough.
mon.bobek@uj.edu.pl, grzegorz.j.nalepa@uj.edu.pl Therefore, in parallel with the BIRAFFE experiments, a dedicated
Copyright c 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Eleventh International Workshop Modelling and Reasoning in Context (MRC) @ECAI 2020 46
framework was developed to automate the preparation of game-based The simplest solution to create an emotional-changing environ-
affective experiments. It allows to generate an experiment template ment was to revolve around the overall difficulty of games. While
with questionnaires between different levels and provides a database- making the neutral, peaceful stage can relieve stress for the player,
based logging interface. A detailed description of the framework can the loud and hard level can intensify the rage and increase heartbeat.
be found in Section 5. Therefore, three genres have been selected: roguelike, platform, and
maze. The first level is balanced to be an easy stage, supposed to de-
velop energetic, happy emotions. On the contrary, the second level is
3 THE BIRAFFE2 EXPERIMENT extremely hard to beat, filled with traps, to give the sensation of un-
The BIRAFFE2 study included 103 participants (33% female) be- just and fury. This juxtaposition is important to the study, given the
tween 18 and 26 (M = 21.63, SD = 1.32), recruited among students sudden change. Last phase is neutral, without any emotion-boosting
of the Artificial Intelligence Basics course at AGH University of Sci- elements, it exists to check the player’s decision-making, behavior
ence and Technology, Kraków, Poland and their friends. and bodily changes due to previous irritation. Additionally, a proper
It is a revised version of a previous experiment called BIRAFFE1 collection of game patterns was implemented. For every stage, de-
(Bio-Reactions and Faces for Emotion-based Personalization) de- pending on what emotions it should boost, from that collection sepa-
scribed in [8].The aim of the study was to collect physiological data rate elements were chosen.
paired with behavioral data, which can then be used to develop mod-
els for prediction of emotions.
Behavioral data were twofold: from the part in which the subjects
played three games (for details see Section 4) and from the classi-
cal experiment, in which sound and visual stimuli (from IADS [2]
and IAPS [9] datasets respectively) were presented and then subjects
were asked to assess what emotions they evoked. Specifically, the
stimuli was presented for 6 seconds, what was followed by 6 seconds
for affective rating with the use of custom widget with 2-dimensional
space (valence and arousal). The whole behavioral data was collected
as a set of logs in comma-separated (CSV) files.
Physiological signals, Electrocardiogram (ECG) and Electroder-
mal activity (EDA), were gathered using BITalino (r)evolution kit,
as it is the most promising of cheap mobile hardware platforms (for
comparison see [7]). Besides ECG and EDA, during the experiment
also the following signals were collected: accelerometer and gyro- Figure 1. Stage 1: an example screen of the game
scope from gamepad, facial images taken by webcam (every 250
milliseconds), screencast of the whole game session.
The whole protocol consisted of several phases:
Stage one contains elements such as score tracking, weapons, en-
1. NEO-FFI paper-and-pen questionnaire [15] for personality mea- emies and looting. The finishing condition is elimination of all an-
surement (approx. 10 minutes), tagonists – no stress-inducting time limit was implemented. The dif-
2. Physiological devices setup (approx. 2 minutes), ficulty in this level was balanced by setting the damage per second
3. Baseline signals recording (1 minute), of the protagonist much higher than the one of the antagonist. While
4. Instructions and training (approx. 5 minutes), players can shoot up to 5 projectiles per second, enemies can shoot
5. First part of stimuli presentation and rating (17.5 minutes), only one attack per second. Moreover, the speed of player’s projec-
6. Games session (up to 15 minutes in total), tiles is 2.5 times higher for the default weapon. An additional blaster
7. Second part of stimuli presentation and rating (17.5 minutes), was placed on a map, giving the possibility for the user to eliminate
8. Three paper-and-pen GEQ questionnaires [5] (one for each game) the enemies even easier. Furthermore, in the case the subject is not
and gaming experience questionnaire (approx. 10 minutes). used to playing games, health points can be increased by picking up
heart-shaped objects. In order to unleash more fun and any form of
The whole protocol lasts up to 75 minutes. Steps 3-7 were done on achievement-getting sensation, a score tracker is incrementing when
a PC. All of them were controlled by the Python 3.8 with the use of picking up money bags from the floor or from the killed enemy (the
PsychoPy 3.2.4 library [13]. Participant interacted with the procedure amount of bags dropped from antagonist is random).
only with a gamepad. In the platform game (stage 2) traps and time limit were imple-
mented. Both of them are crucial in order to imply stress and rage.
4 EVOKING EMOTIONS WITH AFFECTIVE Until the end of the game, the player has to go through the whole
GAMES level. However when the player dies, he respawns in the last check-
point – a yellow flag with letter ’C’; when touched, a happy, although
In order to support the game sessions of the experiment, three specific very distorted sound is played. There are two possible ways for the
affective mini-games were created [16]. The aim for all the games protagonist to lose: falling down off the stage, or stepping into a spike
was to create an immense amount of emotions in a short time. The trap. Considering the fact that this level is supposed to be insanely
main obstacle was the inability to create an intriguing story, therefore hard to get through, two additional traps were implemented to basic
the whole section of narrative elements was discarded. The only way blocks. The first type is an invisible block – before the protagonist
of building an affective project was to make different sets of games collides with them, they are not to be seen in any way by the user. If
with a variety of mechanics and audiovisuals. the player dies after triggering the visibility, it is once again set to in-
Copyright c 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Eleventh International Workshop Modelling and Reasoning in Context (MRC) @ECAI 2020 47
visible. Similar mechanics is once again used for next type of traps – every stage. They were proven to change the state of user’s emo-
falling blocks. Once the collision with the user happens, blocks start tion by their degree of affectiveness. This level was separated into
to fall down. two values – intensity of the feeling (arousal) and pleasantness of a
sound. Depending on these two values, proper sounds were chosen
and included in the games.
Sound Pleasure Arousal
Puppy 2.88 4.91
Bees 2.16 7.03
Vomit 2.08 6.59
Babies cry 2.04 6.87
Baby cry 2.75 6.51
Scream 2.05 8.16
Figure 2. Stage 2: falling block Figure 3. Stage 2: falling block Child abuse 1.57 7.27
before trigger after trigger Applause 7.32 5.55
Rollercoaster 6.94 7.54
Colonial music 6.53 5.84
Bugle 6.32 6.35
Rock n roll 7.90 6.85
Funk music 6.94 5.87
Table 1. Affective sounds used in study
Furthermore, music themes and in-game sounds were recorded.
Figure 4. Stage 2: invisible block Figure 5. Stage 2: invisible block The design was created with a view to expected emotions. First
before trigger after trigger game’s theme consists of electronic/rock music, sounds of picking
items are clear, echo has been added to each sound. To keep the sec-
For the last game in stage 3 memorizing the way through a maze is ond level unbalanced and irritating, time signature for background
the only important part. No time nor score tracking is implemented. music was disturbed – the last eighth note was erased. This gives
Visuals are very simple, no distracting elements were added. The an unsettling feeling, like someone has been playing off tempo. Ad-
choices made by the player are saved into logs, which will be dis- ditionally, each time the player dies increases the pitch and distor-
cussed later on. tion effects for the background theme. Protagonist has a high-pitched
Size and shape of colliders were also adjusted to the game genre voice, which gets more infuriating with every death. The sound of
and difficulty intended. For the first scene, the collider for the protag- winning (which is hard to achieve, given the difficulty of the game)
onist is smaller than his real model. It removes the feeling of being has a very disappointing and unsatisfying tone. Last level has a pleas-
hit before the projectile hits the player. On the contrary, in the sec- ant theme, edited to sound like old arcade, 8-bit music.
ond game colliders are too big. Player can get hit by a trap before In order to get as much as possible from single gameplay about
he touches it with a model. This decision was made to enhance the the state of players’ emotions, additionally to their bodily functions, a
irritation and the feeling of unjust. For the last level, colliders were proper context-gathering mechanism is required. It is implemented as
adjusted to not hit the walls too often, so the movement will be pleas- a set of different event logs that are saved for each stage. Some infor-
ant and smooth. Another intentional difference in stage two from mation is constantly saved, no matter the level – the data about cur-
others is the protagonist’s movement. It was designed similarly to rent player’s position, ID and timestamp of an affective sound played
the jumping mechanics, although it doesn’t stop at a certain speed – in the background. For stage one, events such as killing an enemy,
the player’s model is constantly given acceleration. This is a per- death, the amount of all objects picked up, current state of health and
fect example of poorly made mechanics, which are incredibly hard points are saved with the proper timestamp. Additionally, the amount
to control. of projectiles shot and their accuracy is recorded – this gives more in-
sight on the aggressiveness and gaming experience. There are no en-
emies and pickable items in the second stage, therefore the distortion
rate of music, number of deaths and the data about traps triggered is
saved for every iteration. In the last stage, the amount of dead ends
encountered and the data about going off the correct path is being
saved.
All of the games were developed using the Unity Engine. It is a
powerful environment, with tons of possibilities. One of many fea-
tures used are previously mentioned colliders. The engine contains a
Figure 6. Stage 3: protagonist colliders for different stages. variety of collider shapes, components and traits. For instance, Box
Colliders were used not only as physical objects, but also as triggers
in rooms for the first stage, logging in the third level etc. Animations
in all games were handled through the Animator Controller feature.
To boost the affective part of gameplay, sounds provided by NIMH Another remarkable example for the possible power of Unity Engine
Center for the Study of Emotion and Attention [2] were added to the is Camera - just a simple change in view can drastically change the
Copyright c 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Eleventh International Workshop Modelling and Reasoning in Context (MRC) @ECAI 2020 48
Figure 8. ’Feedback’ option available in menu
Figure 7. Illustration on how the data about wrong path is saved
perception of the player. While first-person cameras can increase the
immersion with the protagonist, third-person cameras can give an in-
sight on what’s going on around the character, escalating the feeling
of stress for the subject. Moreover, sounds and music have separate Figure 9. Plugin’s use case diagram
components - Audio Listener and Audio Source. Both of them have
a simple mixer, included inside the engine. Those components create
impressive opportunities for manipulation of emotion. The simplest
types of questions (radio buttons, slider or dropdown). The plugin
example used in the game is the distortion attribute, for each death in
will create new scene with questions based on the table in database.
the second stage.
After that, a request to manually add generated script-handling data
persistence to an empty object in the scene will pop up. At the end,
5 FRAMEWORK FOR GAME there is a possibility to change the text and position of questions in
CONFIGURATION IN EXPERIMENTS the scene. After building the project, a game is started and the survey
pops up next. When all questions are answered, the framework sends
In order to get information from subjects about their feelings towards all data to the local SQL database.
the games, the GEQ questionnaire was used [5]. This survey consists
of three parts: The Core Questionnaire, The Social Presence Module
and The Post-game Module. All of them contain important informa-
tion about different sections of study. All of them involve questions
about feelings, with a range of possible answers from 0 to 4. Zero
means ’not at all’, one means ’slightly’, two is ’moderately’, three is
’fairly’ and the last, four is ’extremely’. First part of the survey has
33 questions about emotions and sensations felt during the game, for
example: ’I was good at it’ and ’I felt frustrated’. The Social Presence
Module contains 17 questions, however it should only be taken when
any form of social interactions were taken in game, whether it’s an-
other person or a simple non-playable character interaction. The last
section involves 17 questions about the overall feeling of a subject Figure 10. Survey example
after the game has been played, for instance: ’I felt satisfied’ and ’I
found it a waste of time’.
To make this questionnaire a part of study, and also to provide a
unified context-logging mechanism, a software framework has been This framework has a very high potential for further studies.
written. It is responsible for starting all mini-games and preparing the Firstly, it gives an opportunity to create a multi-platform study. More
survey after each game. To install the plugin you need to copy .dll computers would be available to use for a study. Furthermore, a mo-
files and prefabs into Unity project. After restarting the editor, you bile version could be implemented. This way, even more subjects
should see “Feedback” menu in the menu bar and the configuration would’ve taken part in a study. Another possible future usage is the
file in “/Resources” directory. In order to start using the plugin, you adjustment of level difficulty for every game, dependent on answers
need to create an SQL database with tables for each survey form you in the survey. This would increase the affective part of study, as per-
want to include in your game. By default the plugin saves answers sonal change in games would take place.
as integers, so each question should have a separate column of this
type.
Everything is connected through a proper configuration file. It is 6 RELATED WORK
required to set correct database provider and connection string. Af-
ter that, the model classes can be generated by choosing “Generate There are quite a few different frameworks for affective research.
model classes” button from “Feedback” menu. Pressing "Create sur- On the one hand, one can point out the tools used to build classical
vey form" button will open wizard that allows to choose different psychological experiments, like PsychoPy [13], OpenSeasame [10],
Copyright c 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Eleventh International Workshop Modelling and Reasoning in Context (MRC) @ECAI 2020 49
or E-Prime2 and on the other hand, the tools used for affective ex- most popular operating systems. We also tested it with different
periments with games, e.g. FILTWAM [1], iHEARu-PLAY [4], or databases including remote MySQL databases and SQLite database
emoCook [3]. for Android systems, where in both cases it worked correctly. While
The tools in the first group offer various widgets for collecting experiments presented in this paper did not use the framework, they
information from users, making it possible to transfer virtually any will be used by us as a baseline for future evaluation of the frame-
paper questionnaire to the electronic version. However, they do not work.
allow one to control a stimulus-rich game environment. This problem
has been addressed in the second group of tools, where affective in-
teraction is carried out in games (e.g. educational game “emoCook”).
8 FUTURE WORK AND SUMMARY
Nevertheless, these solutions are prepared for specific applications In the paper we presented our recent work conducted as a part of the
and do not provide a general solution for affective experiments. BIRAFFE2 experiment in Affective Computing. As a novel part of
The framework described in this paper combines the advantages the experiment we developed three specially designed mini-games,
of these two groups. It both allows for the use of games as a research based of carefully selected game mechanics. We believe, that games
environment and is a general solution, allowing for the inclusion of provide a controllable yet overall ecological environment for study-
any games (written in Unity) and any questionnaires (the application ing emotions. We used these games as an important counterpart of
is not limited to the GEQ described in the article). classical visual and auditory stimuli during the experiment to evoke
emotions of participants. Moreover, we presented a software tool,
7 EVALUATION with a built-in context-logging mechanism, supporting the execution,
automation and evaluation of experiments of this kind.
The motivation to introduce a few short mini-games was better con- In the future, we would like to develop our work in several di-
trol over the emotions evoked during the experiment. The assumption rections. First of all, based on the analysis of the results of the ex-
was that each game aim is to evoke specific emotions using a small periment, we will continue the development of new games with im-
number of stimuli. These assumptions were confirmed by the results proved mechanics to fine tune the evocation of emotions. Ultimately,
of the GEQ questionnaire. we expect games will help us in developing computer-based person-
Revised list of GEQ factors [6]3 was used for analysis. A series alized models of emotions to be used in different applications. Fur-
of one-way ANOVAs was conducted to evaluate the differences be- thermore, based on the future findings, we would like to study the
tween games. Post-hoc comparisons were done using the Tukey HSD aspects of emotional adaptation and personalization in games using
test. Analysis was performed in Python with scipy4 and statsmodels5 the machine learning methods. Finally, our current setup is ready to
libraries. be used not just in desktop games, but also on mobile devices. We
The strongest effects can be observed for the second level, which will explore this direction, as mobile games not only constitute a
should give the sensation of unjust and fury. It was connected with very important market for games, but also offer new opportunities
significantly higher Negativity (M = 2.85), significantly lower for interaction.
Positive Affect (M = 1.14) and significantly lower Competence6
(M = 0.86) than the two other stages (Negativity: M = 1.11 and
M = 0.70, Positive Affect: M = 2.53 and M = 2.49, Competence: REFERENCES
M = 2.42 and M = 2.78, for Stage 1 and Stage 3 respectively). [1] Kiavash Bahreini, Rob Nadolski, and Wim Westera, ‘FILTWAM - A
Stage 1, designed as an easy stage connected with positive emo- framework for online affective computing in serious games’, in Fourth
tions, and Stage 3, designed as emotionally neutral, were both eval- International Conference on Games and Virtual Worlds for Serious Ap-
uated as the ones with the higher Positive Affect (there were no sig- plications, VS-GAMES 2012, Genoa, Italy, October 29-31, 2012, eds.,
Alessandro De Gloria and Sara de Freitas, volume 15 of Procedia Com-
nificant differences between them). Neutrality of the third level is puter Science, pp. 45–52. Elsevier, (2012).
revealed with the lowest Negativity (M = 0.70; significantly lower [2] Margaret M. Bradley and Peter J. Lang, ‘The international affective
than the first level, M = 1.11). digitized sounds (2nd edition; iads-2): Affective ratings of sounds and
Flow, indicating whether or not players have lost control of their instruction manual. technical report B-3’, Technical report, University
time in the game, was significantly lowest in the third level (M = of Florida, Gainsville, FL, (2007).
[3] Jose Maria Garcia-Garcia, Victor M. Ruiz Penichet, María Dolores
1.35) than the other two levels (M = 1.99 and M = 2.02), indi- Lozano, Juan Enrique Garrido, and Effie Lai-Chong Law, ‘Multimodal
cating that for this factor the most important is the fact that emotions affective computing to enhance the user experience of educational
are evoked, no matter whether they are positive or negative. Finally, software applications’, Mobile Information Systems, 2018, 8751426:1–
Immersion, the subjective connection to the game, was low for all 8751426:10, (2018).
[4] Simone Hantke, Florian Eyben, Tobias Appel, and Björn W. Schuller,
levels (M = 1.75, M = 1.23, M = 1.66 for levels 1-3 respec- ‘ihearu-play: Introducing a game for crowdsourced data collection
tively), which is also consistent with the assumptions. The games for affective computing’, in 2015 International Conference on Affec-
were too short for the players to get fully involved. tive Computing and Intelligent Interaction, ACII 2015, Xi’an, China,
We tested the framework on several platforms including Windows, September 21-24, 2015, pp. 891–897. IEEE Computer Society, (2015).
Linux and mobile platforms running Android operating systems. It [5] Wijnand A. IJsselsteijn, Yvonne A. W. de Kort, and Karolien Poels, The
Game Experience Questionnaire, Technische Universiteit Eindhoven,
ran correctly on all of the platforms7 proving its portability between 2013.
[6] Daniel M. Johnson, M. John Gardner, and Ryan Perry, ‘Validation of
2 See: https://pstnet.com/products/e-prime/.
two game experience scales: The player experience of need satisfac-
3 The values are ranging from 0 (not at all) to 4 (extremely) for each factor.
tion (PENS) and game experience questionnaire (GEQ)’, Int. J. Hum.
4 See: https://www.scipy.org/.
Comput. Stud., 118, 38–46, (2018).
5 See: https://www.statsmodels.org/.
[7] Krzysztof Kutt, Wojciech Binek, Piotr Misiak, Grzegorz J. Nalepa, and
6 Competence reflects how well players judged their own performance against
Szymon Bobek, ‘Towards the development of sensor platform for pro-
the game’s goals. cessing physiological data from wearable sensors’, in Artificial Intel-
7 The only requirement is to use Unity build 2019.2.19f1
ligence and Soft Computing - 17th International Conference, ICAISC
Copyright c 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Eleventh International Workshop Modelling and Reasoning in Context (MRC) @ECAI 2020 50
2018, Zakopane, Poland, June 3-7, 2018, Proceedings, Part II, pp. 168–
178, (2018).
[8] Krzysztof Kutt, Dominika Drażyk,˛ Paweł Jemioło, Szymon Bobek,
Barbara Giżycka, Víctor Rodríguez Fernández, and Grzegorz J. Nalepa,
‘BIRAFFE: Bio-reactions and faces for emotion-based personaliza-
tion’, in AfCAI 2019: Workshop on Affective Computing and Context
Awareness in Ambient Intelligence, volume 2609 of CEUR Workshop
Proceedings. CEUR-WS.org, (2020).
[9] Peter J. Lang, Margaret M. Bradley, and B. N. Cuthbert, ‘International
affective picture system (iaps): Affective ratings of pictures and instruc-
tion manual. technical report B-3’, Technical report, The Center for
Research in Psychophysiology, University of Florida, Gainsville, FL,
(2008).
[10] Sebastiaan Mathôt, Daniel Schreij, and Jan Theeuwes, ‘OpenSesame:
An open-source, graphical experiment builder for the social sciences’,
Behavior Research Methods, 44(2), 314–324, (2012).
[11] Grzegorz J. Nalepa, Krzysztof Kutt, and Szymon Bobek, ‘Mobile plat-
form for affective context-aware systems’, Future Generation Com-
puter Systems, 92, 490–503, (mar 2019).
[12] Grzegorz J. Nalepa, Krzysztof Kutt, Barbara Giżycka, Paweł Jemioło,
and Szymon Bobek, ‘Analysis and use of the emotional context with
wearable devices for games and intelligent assistants’, Sensors, 19(11),
2509, (2019).
[13] Jonathan Peirce, Jeremy R. Gray, Sol Simpson, Michael MacAskill,
Richard Höchenberger, Hiroyuki Sogo, Erik Kastman, and
Jonas Kristoffer Lindeløv, ‘Psychopy2: Experiments in behavior
made easy’, Behavior Research Methods, 51(1), 195–203, (2019).
[14] Rosalind W. Picard, Affective Computing, MIT Press, Cambridge, MA,
1997.
[15] Bogdan Zawadzki, Jan Strelau, Piotr Szczepaniak, and Magdalena Śli-
wińska, Inwentarz osobowości NEO-FFI Costy i McCrae. Polska adap-
tacja, Pracownia Testów Psychologicznych, Warszawa, 1998.
[16] Laura Żuchowska, Game Design with Unity for Affective Games, BSc
thesis, AGH University of Science and Technology, 2020. Supervisor:
G.J. Nalepa.
Copyright c 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).