Conference PaperPDF Available

“I Miss Going to that Place”: The Impact of Watching Nature Videos on the Well-Being of Informal Caregivers

  • Interactive Technologies Institute / LARSyS


Informal caregivers play an essential role in caring for persons who require assistance and in managing the health of their loved ones. Unfortunately, they need more health, leisure, and relaxation time. Nature interaction is one of many kinds of self-care intervention. It has long been regarded as a refreshing break from stressful routines, and research suggests exposure to nature interventions to improve the quality of life of caregivers. Despite not being the real thing, technology allows us alternatives that can still have some beneficial effects. In this preliminary study, we explore the benefits of natural environment videos on informal caregivers as an alternative to exposure to nature. Specifically, we are interested in the effects of their own choices versus a random video. We found that natural environment videos improve the well-being of informal caregivers in at least three key areas: valence, arousal, and negative affect. Furthermore, the effect increases when they choose the video they want to watch instead of a random video. This effect benefits the studied subjects because they need more time and energy to visit real natural environments.KeywordsInformal caregiversSelf-careWell-beingNature videos
“I Miss Going to that Place”: The Impact
of Watching Nature Videos on the
Well-Being of Informal Caregivers
Beatriz Peres1,2,3(B
), Hildegardo Noronha1,2 , Daniel S. Lopes4,5 ,
Joaquim Jorge3,5 , and Pedro F. Campos1,2,6
1University of Madeira, Funchal, Portugal
2Interactive Technologies Institute, LARSYS, Funchal, Portugal
3INESC-ID, Lisbon, Portugal
4Interactive Technologies Institute, LARSYS, Lisbon, Portugal
5Instituto Superior ecnico, Universidade de Lisboa, Lisbon, Portugal
6WoW Systems, Funchal, Portugal
Abstract. Informal caregivers play an essential role in caring for per-
sons who require assistance and in managing the health of their loved
ones. Unfortunately, they need more health, leisure, and relaxation time.
Nature interaction is one of many kinds of self-care intervention. It has
long been regarded as a refreshing break from stressful routines, and
research suggests exposure to nature interventions to improve the qual-
ity of life of caregivers. Despite not being the real thing, technology allows
us alternatives that can still have some beneficial effects. In this prelim-
inary study, we explore the benefits of natural environment videos on
informal caregivers as an alternative to exposure to nature. Specifically,
we are interested in the effects of their own choices versus a random
video. We found that natural environment videos improve the well-being
of informal caregivers in at least three key areas: valence, arousal, and
negative affect. Furthermore, the effect increases when they choose the
video they want to watch instead of a random video. This effect benefits
the studied subjects because they need more time and energy to visit
real natural environments.
Keywords: Informal caregivers ·Self-care ·Well-being ·Nature videos
1 Introduction
Informal caregivers play an essential role in caring for persons who require assis-
tance and in managing the health of their loved ones. However, coping with
heavy responsibilities, like personal care or domestic activities, and securing
income may absorb most informal caregivers’ time budget, leaving little to no
time for them to attend to their health, leisure, and relaxation [19]. This issue
is vital as informal caregiving, besides being time-consuming, is also physically
and emotionally demanding [13].
The Author(s), under exclusive license to Springer Nature Switzerland AG 2023
J. Abdelnour Nocera et al. (Eds.): INTERACT 2023, LNCS 14145, pp. 23–32, 2023.
24 B. Peres et al.
Self-care is defined by Cook [7] as the process of being aware of and attending
to one’s basic physical and emotional needs daily through engaging in beneficial
behaviors, which may include modifying one’s daily routine, relationships, and
environment as needed to promote it [7].
Self-care practices are essential to informal caregivers since they positively
impact mental health [17]. This matter emphasizes the importance of a build-
up of interventions addressing the needs of informal caregivers to reduce stress
and improve well-being. Some interventions help reduce the adverse effects of
care and enhance caregivers’ quality of life. Psychoeducational, psychothera-
peutic, self-help, multi-component interventions that give disease or self-care
knowledge, problem-solving approaches, communication skills, social support,
or mindfulness are examples of these measures [10].
However, these interventions are typically costly and unavailable to everyone,
and informal caregivers may need more time for them [5]. Furthermore, interven-
tions that incorporate various activities to promote multiple outcomes, such as
social support, psychological abilities, and a healthy lifestyle, have been linked
to a reduction in burden and an increase in healthy living behaviors [7]. These
interventions demonstrate the need to promote and practice self-care, particu-
larly among informal caregivers, since it relates to improved physical, emotional,
and mental health [7].
Nature interaction is a self-care intervention. It has long been regarded as
a refreshing break from stressful routines. For instance, Lehto et al. [13] found
that further research is required to support informal cancer caregivers. Neverthe-
less, they still suggest exposure to nature interventions, considering the benefits
of the natural environment. Human health and well-being have been shown to
benefit from interaction with nature and green environments [16].Shinrin-Yoku
(Forest Bathing) [14], is the practice of spending time in the forest, which pro-
motes better health, a more robust immune system, happiness, and calmness.
According to Qing Li’s research [14], being around trees, filling the home with
house plants, and vaporizing essential tree oils can reduce stress and improve
health and well-being by interacting with nature.
These interactions have several physiological effects, including decreased sali-
vary cortisol, heart rate, diastolic blood pressure, HDL cholesterol, decreased
low-frequency heart rate variability (HRV), and increased high-frequency HRV
[20]. It also has psychological effects such as positive effects on energy scores,
tranquility, heightened levels of happiness, self-transcendent emotions (like awe,
gratitude, and wonder), and an increased sense of well-being [2] improved atten-
tion levels [2], decreased depression [18], anxiety [2], stress levels [21] and reduced
negative emotions such as anger, fatigue, and sadness [2]. Natural environments,
such as forests, have been studied extensively, with findings indicating that they
benefit human physical and mental health [11,15].
Nature’s psychological effects on well-being can also be noticed without direct
physical contact with nature. Examples include nature videos [23] and virtual
reality nature experiences [1]. In addition there are digital representations of
nature in the form of nature videos on digital platforms [23], for example, in
I Miss Going to that Place 25
online nature activities1, and webcam travel (i.e., seeing location-based web-
cams online) [12]. For people with pre-existing health concerns, digital nature
engagement provided a valuable opportunity to access other natural locations,
allowing for a sense of escape and fostering nostalgia by establishing linkages to
familiar or preferred locales [8].
When in-vivo nature is absent, Darcy et al. [8] findings agree to some extent
that digital nature can supplement or serve as a suitable replacement. However,
this may not be a sufficient substitute for ‘real’ nature encounters. For example,
a lack of access to specific natural places has resulted in confused sensations or
when digital nature fails to deliver a comprehensive sensory experience [8].
Alternatives to real-life nature may improve well-being. However, the impacts
of actual [23] are worth noting. Digital nature surrogates (i.e., nature videos,
photos, Virtual Reality) can help as they may improve well-being, particularly for
informal caregivers who do not have the possibility to experience direct contact
with nature.
Informal caregivers may not be able to go to a natural environment. Time
constraints due to long working days or immobility may hamper opportunities
for physical nature experiences. In addition, only some can access nature easily,
as many people may not have the physical constitution or mobility to access
nature areas. With this, informal caregivers could use technology to connect
with nature without leaving home, such as watching videos that bring natural
environments into their homes. However, no study was found using relaxing
nature videos with informal caregivers that could allow them to take a break
from their caregiving duties and focus on their health and well-being.
1.1 Research Question and Contributions
This preliminary study tries to pull informal caregivers closer to nature through
nature environment videos. We aim to analyze whether watching chosen relaxing
nature videos can impact the well-being of informal caregivers, as it appears that
personal preference can improve well-being. For this reason, we try to answer
the following research question:
Will watching relaxing nature videos of their choice improve informal care-
givers’ well-being versus watching a random nature video?
The contribution of this paper lies in analysing and interpreting the findings
regarding the effects of watching a chosen nature video versus a random video
on informal caregivers’ well-being.
2 Methods
2.1 Elicitation of Preferences
We used a questionnaire to ascertain the characteristics that informal caregivers
like in forest, beach, and mountain environment videos. We then asked the par-
1Discover Small Moments of Joy in Nature, 2020; The Wildlife Trusts over 1000 Care
Homes Sign-Up to Go Wild This June 2020.
26 B. Peres et al.
ticipants to choose the type of environment videos they wanted to watch. After
watching three different videos of the chosen type, we asked what they liked
about the videos and what they would change. The answers provided insights
into their emotions and feelings during the video visualization. The selected
characteristics were: the videos can not have people, the forest and mountain
video should be during the day, and the beach environment should have a sun-
set. This allowed us to preselect three videos for this study, what metrics should
be considered, and their possible effects on the informal caregivers’ well-being.
2.2 Sample
The subjects of this study are all informal caregivers. A total of thirty partici-
pants completed the study, with 49.7 ±9 years old. A significant percentage of
the participants were female (86.7%). More than half of the participants (60%)
became caregivers because of a family member’s disease - 26,7% of them were
daughters or sons of the diseased person, and 16.7% were parents. The average
time being a caregiver was 9.3 ±6.2 years.
2.3 Data Collection
We used several questionnaires to gather data from the subjects. We started by
asking the subjects about their age, gender, why they became informal care-
givers, their relationship to the family member they cared for, and how long
they had been doing informal caregiving.
We then used the Self-Assessment Manikin (SAM) [3] to measure the emo-
tional states (valence, arousal, and dominance). For this study, we did not mea-
sure dominance as it is irrelevant. We also used the Positive and Negative Affect
Schedule (PANAS) [22] to measure mood and emotion.
Finally, we administered three ad hoc satisfaction questions to assess the
user’s experience watching the nature environment videos. The questions were:
a) What natural environment did you choose and why? b) What feature do you
like in the natural environment video? c)What changes would you like to make
in the natural environment video?
2.4 Tasks
The participants watched two nature environment YouTube videos in two dif-
ferent conditions from a preselected list based on the feedback of the initial
questionnaire. The list had three nature videos (forest, beach, and mountain) 2.
After watching each video, participants had to fill out two self-reported scales.
2Forest video: (starting at min 15); Beach video: (starting at min 15); Mountain video: https:// (starting at min 1).
I Miss Going to that Place 27
2.5 Procedure
Individuals were invited to participate in the study in their home environment,
in a calm environment, and using a mobile phone to watch nature videos. First,
they signed the informed consent to participate in the research. Then, they filled
out a socio-demographic survey. Then, the study was composed of phases from
T0 to T2. In phase T0, and to establish a baseline, they filled out the SAM and
PANAS scales.
In phrase T1, the participants were randomly assigned either a choice con-
dition or a random one for the first video, followed by the opposite condition
for the second video in phrase T2. In the choice condition, the participant can
freely choose the video they want to watch, while on the random condition, the
participant gets to watch a randomly selected video. We alternate the conditions
(choice and random) to avoid the order effect. After watching the video, par-
ticipants filled out the SAM and PANAS scales in each condition, administered
during phase T0.
In both phrases T1 and T2, participants watched each video for five minutes,
as research shows that a 5-minute video can induce positive physiological change
[4,6,9]. Therefore, we selected this duration to keep the experiment short but
with relevant results.
In the end, the participants answered post hoc questions about why they chose
that video and what features they liked and disliked in the natural environment
video. Figure 1illustrates each nature video used in this study.
Fig. 1. Screenshots of each nature environment video
2.6 Data Analysis
The data were analyzed using the Friedman test using SPSS Statistics ‘26’.
The Friedman test is a non-parametric test used when measuring an ordinal
dependent variable. It is also applied to check for changes within people (repeated
measures) and within a group measured in three or more conditions. We applied
the Friedman test because we had three conditions, repeated measurements, and
ordinal data. Since the Friedman test was significant, we had to examine where
the differences occurred. We conducted a separate post hoc analysis on each
combination using the Wilcoxon pairwise test.
28 B. Peres et al.
Given that, we needed to adjust the p-value on the Wilcoxon test results
since we were performing multiple comparisons. To calculate the p-value adjust-
ment, we divided the previous significant level (0.05) by the number of tests we
conducted, yielding a new significant level of 0.017 (0.05/3). If the p-value was
higher than 0.017 was not a significant result. The participant’s responses to
the open-ended question were analyzed by two authors using thematic analysis.
Starting by creating initial codes, then grouping codes into themes, reviewing
and revising themes, grouping all excerpts associated with a particular theme,
and writing the narrative.
3 Results
There was a statistically significant difference in valence, arousal, and negative
affect, X2(2) = 11.146 (degrees of freedom = chi-square), p 0.001, X2(2) =
21.843, p 0.001, X2(2) = 34.758, p 0.001, respectively. However, no statisti-
cally significant difference was found in positive affect X2(2) = 5.845, p 0.05.
Wilcoxon’s post hoc analysis adjusted the significance level to p = 0.017.
Valence showed a statistically significant increase between the baseline and
the choice condition (p 0.001, r = 0.54). However, there was no significant
difference between the baseline and the random condition (p 0.05 r = 0.33).
Arousal showed a statistically significant decrease between the baseline and ran-
dom condition (p 0.001, r = 0.68) and between the baseline and choice con-
dition (p 0.001, r = 0.58). Negative Affect showed a statistically significant
decrease between the baseline and the random condition (p 0.001, r=0.76),
between baseline and choice condition (p0.001, r = 0.79). Figure 2illustrates
the distribution of values for a better understanding of the results.
Most participants (n = 20) chose the beach as the environment they preferred
to watch, nine chose the forest, and only one chose the mountain. Participants
made their choices based on the following reasons: “it brings peace”, “it helps to
calm down”, “it renews energy”, “it gives a feeling of freedom”, “it relaxes”, “it
feels light”, “it takes away the sadness”, “it brings tranquility”, and “it makes
them feel good”. Some participants mentioned that “it is my environment”, “I
live in the countryside”, and “I like contact with nature”. Some participants
mentioned “a feeling of missing going to that place”, “the smell of the sea”,
“listening to the waves”, and “I miss that”. Some participants justified that
they do not go to this natural environment with: “there is no possibility of great
absence”, “it is a bit distance from home and I can not leave my family member
alone”, “lack of time”, “lack of money for fuel”.
Some participants would like to change the type of environment, the light,
the birds’ sound, and the green colors of the forest video. They liked the sunset
and the sound of the waves in the beach video, but some mentioned they would
change the sound to a more relaxing one. In the mountain video, they liked the
type of environment and the light but would also change the sound.
I Miss Going to that Place 29
Fig. 2. Box and Whiskers plot of Valence, Arousal and Negative Affect with corre-
sponding Random and Choice
4 Discussion
The main goal of this paper was to explore the impact of natural environment
videos on informal caregivers with a focus on the act of choosing. We did find a
statistically significant difference in valence, arousal, and negative affect between
the baseline and the choice condition. In addition, the negative affect and arousal
also have a statistically significant difference between the random and choice
Having a statistically significant increasing effect on valence seems to indicate
a benefit of nature videos. However, in this study, the effect only appears when
the subjects choose the video. This may indicate that the choice does matter
for valence. Arousal and Negative Affect have a statistically significant decrease.
There is a more prominent effect for the random condition for the arousal, while
the negative affect has a similar size in both conditions. This finding may indicate
that the choice has a small or negligent effect on both arousal and negative affect
relative to the base condition.
We surmised that the effects found in valence, arousal, and negative affect
might depend on previous feelings and experiences gathered on visitations to
similar places. This idea of “gathered experience” highlights how certain places
can become emotionally significant. This is supported by how the participants
justified the choices with feelings of calmness and peacefulness. In this case, the
positive emotional state is associated with an entire scene or specific sensory
stimulation, visual or auditory, that evoked familiarity and nostalgia.
5 Study Limitations and Future Work
In this section, we discuss the main shortcomings of our approach and hint at
future research opportunities.
Nature Video Selection: We studied only the effect of two nature videos, and
anticipated that some videos would appeal more to one than others. Due to this,
we requested that participants select the natural video. However, more types
30 B. Peres et al.
of nature videos and giving more options to participants could yield different
Researchers could learn more about why participants selected a particular
nature video, such as which videos they preferred most and how the specific
nature video they selected affected their well-being by letting them select from
a broader range of nature videos. Future research should consider this idea,
and take the hints given by the subjects to create a better and more extensive
selection of videos.
Other Media Types: Although we focused on the effect of watching natu-
ral environments, especially on choosing, looking into looking into other media
forms, such as visual-only and Virtual Reality, is also essential. Other forms of
media should be researched to determine which media the act of choosing has the
best effect on the informal caregiver’s well-being. These findings could be used
to develop other approaches to promote the well-being of informal caregivers.
Regarding the act of choosing, the importance of choice must be further
studied to understand its true impact, possibly with additional metrics.
Duration of the Study: Our short-term study provided exciting results.
However, a study with more repetitions and a longer duration could provide
a stronger case, so we could benefit from doing it in a future study.
6 Conclusion
We conclude that watching a chosen nature video improves the well-being of
informal caregivers in at least three key areas: valence, arousal, and negative
affect. The choice made by the participants improves the effect on valence.
These results are important because many informal caregivers need help entering
real natural environments. By viewing chosen nature videos, they can experi-
ence the calming effects of nature while in their own homes. By viewing nature
videos, informal caregivers can escape caregiving’s physical, emotional, and men-
tal fatigue, feel more relaxed and less stressed, and improve their well-being
without leaving home. Therefore, providing informal caregivers access to nature
videos is an effective and empowering way to provide them with moments of
self-care that can positively impact their physical, mental, and emotional health.
Caregivers can also find comfort in the choice of nature videos allowing them to
take ownership of their caregiving situation and feel empowered to make deci-
sions that promote their physical and emotional health.
Acknowledgments. We are grateful to all the participants that were generous with
their time for this study.
This research was funded by the Portuguese Recovery and Resilience Program
(PRR), IAPMEI/ANI/FCT under Agenda C645022399-00000057 (eGamesLab) and
was supported by PhD FCT grant 2020.08848.BD.
I Miss Going to that Place 31
1. Bodet-Contentin, L., Letourneur, M., Ehrmann, S.: Virtual reality during work
breaks to reduce fatigue of intensive unit caregivers: a crossover, pilot, randomised
trial. Aust. Critical Care 36, 345–349 (2022).
2. Bowler, D.E., Buyung-Ali, L.M., Knight, T.M., Pullin, A.S.: A systematic review
of evidence for the added benefits to health of exposure to natural environments.
BMC Public Health 10, 456 (2010).
3. Bradley, M.M., Lang, P.J.: Measuring emotion: the self-assessment manikin and
the semantic differential. J. Behav. Ther. Exp. Psychiatry 25(1), 49–59 (1994).,
4. Brown, D.K., Barton, J.L., Gladwell, V.F.: Viewing nature scenes positively affects
recovery of autonomic function following acute-mental stress. Environ. Sci. Tech-
nol. 47(11), 5562–5569 (2013). American Chemical Society.
5. Brown, E.L., et al.: CareHeroes web and android apps for Dementia caregivers:
a feasibility study. Res. Gerontol. Nurs. 9(4), 193–203 (2016).
6. Chan, S.H.M., Qiu, L., Esposito, G., Mai, K.P., Tam, K.P., Cui, J.: Nature in
virtual reality improves mood and reduces stress: evidence from young adults and
senior citizens. Virtual Reality (2021).
7. Cook-Cottone, C.P., Guyker, W.M.: The development and validation of the Mind-
ful Self-Care Scale (MSCS): an assessment of practices that support positive
embodiment. Mindfulness 9(1), 161–175 (2018).
8. Darcy, P.M., Taylor, J., Mackay, L., Ellis, N.J., Gidlow, C.J.: Understanding the
role of nature engagement in supporting health and wellbeing during COVID-
19. Int. J. Environ. Res. Public Health 19(7), 3908 (2022). Number: 7. Multi-
disciplinary Digital Publishing Institute.,
9. Gladwell, V.F., et al.: The effects of views of nature on autonomic control. Eur.
J. Appl. Physiol. 112(9), 3379–3386 (2012).
10. Grossman, M.R., Zak, D.K., Zelinski, E.M.: Mobile apps for caregivers of older
adults: quantitative content analysis. JMIR Mhealth Uhealth 6(7), e162 (2018).
11. Hong, S., Joung, D., Lee, J., Kim, D.Y., Kim, S., Park, B.J.: The effects of watching
a virtual reality (VR) forest video on stress reduction in adults. J. People Plants
Environ. 22, 309–319 (2019).
12. Jarratt, D.: An exploration of webcam-travel: connecting to place and nature
through webcams during the Covid-19 lockdown of 2020. Tourism Hospitality Res.
21(2), 156–168 (2021).
13. Lehto, R.H., Wyatt, G., Sender, J., Miller, S.E.: An evaluation of natural environ-
ment interventions for informal cancer caregivers in the community. Int. J. Envi-
ron. Res. Public Health 18(21) (2021).,
32 B. Peres et al.
14. Li, Q.: Shinrin-Yoku: The Art and Science of Forest Bathing. Penguin UK, London
15. Li, Q.: The Art and Science of Japanese Forest Bathing. REVOLVE, p. 4 (2019).
16. Mayer, F.S., Frantz, C.M., Bruehlman-Senecal, E., Dolliver, K.: Why is nature
beneficial?: The role of connectedness to nature. Environ. Behav. 41(5), 607–643
17. Miller, S., Lee, J.: A self-care framework for social workers: building a strong
foundation for practice. Families Soc. J. Contemp. Hum. Serv. 94, 96–103 (2013).
18. Morita, E., et al.: Psychological effects of forest environments on healthy adults:
Shinrin-Yoku (forest-air bathing, walking) as a possible method of stress reduction.
Public Health 121(1), 54–63 (2007).,
19. Oliveira, D., Zarit, S.H., Orrell, M.: Health-promoting self-care in family caregivers
of people with dementia: the views of multiple stakeholders. Gerontologist 59,
e501–e511 (2019)
20. Twohig-Bennett, C., Jones, A.: The health benefits of the great outdoors: a sys-
tematic review and meta-analysis of greenspace exposure and health outcomes.
Environ. Res. 166, 628–637 (2018).,
21. Wang, X., Shi, Y., Zhang, B., Chiang, Y.: The influence of forest resting environ-
ments on stress using virtual reality. Int. J. Environ. Res. Public Health 16(18),
E3263 (2019).
22. Watson, D., Clark, L.A., Tellegen, A.: Development and validation of brief mea-
sures of positive and negative affect: the PANAS scales. J. Pers. Soc. Psychol.
54(6), 1063–1070 (1988).
23. Xu, S., et al.: #Springwatch #WildMorningswithChris: engaging with nature
via social media and wellbeing during the Covid-19 lockdown. Front. Psy-
chol. 12, 701769 (2021).,https://www.
ResearchGate has not been able to resolve any citations for this publication.
Full-text available
People perceive advanced technologies to be nondeterministic as they become increasingly complex and opaque. Therefore, the issue of trust in technology is becoming crucial, particularly in risky domains where the consequences of misuse can cause significant harm or loss. There is a lack of design heuristics that consider the users’ perspective on the trustworthiness of technologies to support practitioners in promoting trust in technologies. In this exploratory study, we aimed to understand how users perceive the trustworthiness of advanced financial technologies. A survey was conducted to assess users’ risk propensity and trust in technology, followed by semi-structured interviews with 12 participants to examine their behaviours and perceptions when using cryptocurrency platforms. We use the observation method to triangulate the data, asking participants to show us how they use the application. The grounded theory analysis identified the following factors that affect users’ perceptions of trustworthiness in advanced financial technologies: Usability, Credibility, Risk Mitigation, Reliability, and Level of Expertise.KeywordsValue-sensitive designHuman-centered design, Human-computer trustTrustworthy technology
Conference Paper
Full-text available
The development of human-computer interaction (HCI) systems that will efficiently capture the human brain, the so-called Brain-Computer Interaction (BCI) systems, will bring a new era in various disciplines (gaming, education, cultural heritage, etc). Actually, it is expected that the design and development of an electroencephalography (EEG) based-driven framework for intelligent real-time modelling of human cognitive abilities will provide groundbreaking technological advances in the delivery of human cognition-centred personalized systems and significantly advance the state-of-the-art research in human brain modelling. The aim of this paper is to make a concise and focused presentation of Signal Processing and Artificial Intelligence (AI) methods, including Machine Learning (ML) and Deep Learning (DL), and how these fields may help to model and thus predict human behaviour, emotion, cognitive state in different tasks.
Social network analysis reveals a significant set of essential information on the behaviour of the players and teams: such as passing sequences between players in the attacking third position of attacking performance. Despite their usefulness, network metrics related to expected goal values for soccer analysis are minimal. Thus, the study compared network approaches that led to Chelsea FC's goal and playing style in the English Premier League in season 21/22. Moreover, ‘expected goal values’ (xG) show the probability of the goal scored, which can be related to the goals scored passing network. The study used centrality in network analysis such as degree prestige, degree centrality, and betweenness centrality to find the significant contributor of the player's position independently during the match that led to the goal scoring and did not consider the playing style of Chelsea FC. Furthermore, the xG values of shots in every game were visualized using Tableau software. A set of adjacency metrics were computed using the highlight videos of goals for every match, and the results of network analysis found that the most received the ball from their teammates were left wing-back and right wing-back, defensive midfielders and right wing-back have the highest degree centrality and attacking midfielder and left wing-back have the highest betweenness centrality. Furthermore, the statistical data from the visualization such as cross percentage, passing percentage, shots and xG percentage can be used to enhance the team performance.KeywordsMatch analysisPassing networkExpected goals
Numerous toolkits have been developed to support ethical AI development. However, toolkits, like all tools, encode assumptions in their design about what work should be done and how. In this paper, we conduct a qualitative analysis of 27 AI ethics toolkits to critically examine how the work of ethics is imagined and how it is supported by these toolkits. Specifically, we examine the discourses toolkits rely on when talking about ethical issues, who they imagine should do the work of ethics, and how they envision the work practices involved in addressing ethics. Among the toolkits, we identify a mismatch between the imagined work of ethics and the support the toolkits provide for doing that work. In particular, we identify a lack of guidance around how to navigate labor, organizational, and institutional power dynamics as they relate to performing ethical work. We use these omissions to chart future work for researchers and designers of AI ethics toolkits.