Tinkering: A Way Towards Designing Transparent Algorithmic User Interfaces

Abstract

With the widespread use of algorithms in interactive systems, it becomes inevitable for the users to apply these algorithms with caution. Algorithms are applied to make decisions in healthcare, hiring, the criminal justice system, and social media news feed among others. Thus, algorithmic systems impact human lives and society in significant ways. As a consequence, currently, the focus has been shifted toward designing transparent algorithmic user interfaces (UI's) - to make the algorithmic aspects more explicit. Designing transparent algorithmic user interfaces requires the designer to bring the algorithmic aspects of control at the UI level without causing information overload. This research attempts to investigate this gap by proposing tinkering or playful experimentation as a means of designing transparent algorithmic UI's. Tinkering is a cognitive style related to problem-solving, decision making, enables exploration with the interactive system. The proposed approach of combining tinkering with transparent UI's serves two potential purposes: first, the exploratory nature of tinkering has the ability to make the algorithmic aspects transparent without hurting users experience (UX), while providing flexibility and suficient control in the personalized interactive experience; second, it enables the designer to detect software inclusiveness issues in the design before they become part of the final software, by allowing us to measure how much algorithmic transparency is desired across diferent user groups.

Keywords

• tinkering
• exploration
• transparent algorithmic user interface
• inclusive design
• algorithmic transparency

1. Research Problem and

© 2021 Copyright © 2021 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0) CPWrEooUrckReshdoinpgs IhStpN:/c1e6u1r3-w-0s.o7r3g (CCEEUURR-WSW.oorrgk)shop Proceedings els and algorithms; in worst, they might enable the users to make a wrong decision. Users

Motivation

trust is violated when these algorithmic sysAlgorithms are rapidly applied in most of the tems produce an outcome that is harmful, biinteractive applications that we use today. For ased, and unethical. As a consequence, someinstance, well-known algorithmic system in- times users end up stop using such product or cludes YouTube for video recommendation, services [6, 7]. Thus, designing transparent COMPAS risk assessment tool [1], Facebook algorithmic user interfaces are getting more News Feed [2] among others. Research shows, and more attention among the research comthat in many cases, these systems generated munity [8] to make the algorithmic aspects predictions might sufer from biases [ 1, 3, 4 ], explicit and more transparent. causing accountability and safety issues [5], Previous research have advocated for transdue to lack of clarity of the underlying mod- parent recommendation systems in various domains [9, 10], transparent statistical research Joint Proceedings of the ACM IUI 2021 Workshops, April practices [11], transparent debugging [12, 13], 13-17, 2021, College Station, USA and transparent journalism [14, 15]. While " [e-mail] (D. Showkat) others have examined and emphasized the importance of transparent data collection process [16, 17]; Microsoft datasheets for datasets presents one example [18, 17] to achieve transparency and accountability during Machine We also do not know how to measure a parLearning (ML) lifecycle for both dataset cre- ticular user groups transparency needs. To ator and dataset consumer. bridge these gaps, we propose a playful ex

Similarly, various techniques are also avail- ploration approach called “tinkering” [32, 30] able to make the underlying algorithmic as- as a way of designing transparent algorithsumptions more open, interpretable, and easy mic UI’s by examining Facebook News Feed. to understand; explanation is one of them [2, There are a couple of benefits of our proposed 19]. Recently, researchers also explored the approach: first, it is possible, that the exploratory potential of socio-technically inspired perspec- nature of algorithm features (matrices) will tive such as Social Transparency (ST) [20], not overwhelm the user by providing the user perhaps, due to the social nature of interpret- suficient algorithmic control in the personability [ 21 ]. Explanation tool or Explainers, alized interactive news feed experience; secalso known as interpretability tool are avail- ond, by enabling the measuring ability at the able as open-source Python packages to de- interface level of how much transparency is scribe both white box and black box models desired for each groups, we include the pos[18, 22, 23, 24]. They provide an easy inter- sibility of transparent interface designs that pretation of the model’s mechanism and out- are inclusive (e.g., gender [33, 34].) We do not come in a trustworthy, transparent, and safer intend to modify or suggest a new facebook manner [25]. Applying these explainers re- ranking algorithm, instead, our main objecquires the user to call pre-defined functions, tive is to encourage a diferent perspective in integration with complex workflows [ 21 ], and the design of transparent algorithmic user inis often “critiqued for its techno-centric view” terfaces. We end our discussion by suggest[20]; and, applying them requires program- ing potential future research directions. ming. Furthermore, as these tools are publicly available and free to use, research shows that even expert data scientists overuse the 2. Related Work explainers (InterpretML [22]) prediction by overly trusting them, and sometimes use them 2.1. Domain Applications and without proper understanding [26]. Algorithmic Transparency

Even though various design guidelines [8, Algorithmic systems are everywhere; they range 27, 7] and principles [13] exists, including ex- from search engine [35], social media news planatory prototypes [13, 12], for designing feed, to video/music or product recommentransparent algorithmic UI’s; however, design dation systems. These systems has the ability approaches considering users personality, cog- to impact and influence the way we perceive, nitive style, problem-solving strategies are still interact and experience the world around us. unexplored. Research in education, psychol- Much of the blessings associated with these ogy, marketing, and other domains indicate systems are not free from its perils [36], in that there exists a significant diference in the many cases, the algorithms are not fair [6]. way diferent users use and process informa- For example, research showed that Google search tion [ 28, 29, 30 ]. We do not know how these algorithm displayed biased and racist content diferent cognitive style or mental processes when queried for certain keywords such as will play out in the case of designing a trans- “black girls” [35]. The absence of context asparent algorithmic system. Likewise, how muchsociated with the search results makes algotransparency is even enough or desired across rithmic interpretation even more dificult [16, diferent critical audience [31] is also unknown. 35]. Researchers also discovered biases in im- tion tools or explainers such as white box and age annotation [ 4 ] in computer vision across black box API’s/packages [18] are available various facets such as race, gender, and weight to describe a wide range of ML models. White [3]. As a consequence, researchers advocated box explainers (glass box or generalized adfor making data’s economic value transpar- ditive models or GAM’s [26]) works directly ent [19], because users will likely stop using on data to explain models such as linear rea technology due to the lack of opacity about gression that is easy to understand; while the how their generated data is actually used. Al- black box explainers (post-hoc explanations) gorithmic transparency has also received a requires input and ML models output to exconsiderable amount of attention in data sci- plain models that are harder to explain such ence work practices [37], medical AI applica- as neural networks [25]. The explainers are tions [38] among many others. The lack of open-source, available in Microsoft’s Azure transparency causes mistrust [6] and dissat- ML packages (e.g., SHAP [42], LIME [32], eli5 isfaction in these systems. There exists an in- [22]), Google Cloud API (e.g., What If Tool creasing opportunity to establish trust through [23]) platforms and also in Python Sklearn transparency with the advancement of digi- libraries. Figure 1 shows the output of calltal media and computer technology [39]. For ing the SHAP summary plot function visualsimplicity, in this paper, we examined algo- ization. These explainers operate on tabular, rithmic transparency in the case of Facebook text, and image data [18, 25]. news feed because it is a well-studied socio- While these tools and visualizations have technical interactive system [2, 40, 41]. Also, helped data scientists to understand the model’s very little is known about how the news feed output in some cases, but it also depends on curation works [41], thus, we wanted to pro- the explainers used. Research showed that pose an early stage transparent algorithmic due to the free availability of these tools, data news feed prototype, to imagine how a trans- scientists misuse them by overly trusting them parent news feed might look like. [26, 5]. These tools are mainly used by data scientists and ML practitioners. However, they 2.2. Explanation, faced numerous challenges such as model inInterpretability, and stability (e.g., LIME, SHAP), tools not scaling with large dataset, dificulty in tool inte

Algorithmic Transparency gration with their workflow [ 21 ]; thus, these Previous research have shown the significance tools may not be accessible to technical nonof explanation (e.g., how, what, why) to achieve experts (e.g., legal professionals) [ 26, 21 ], betransparency in algorithmic systems such as cause applying them requires more than baFacebook news feed curation [19, 2]. Expla- sic programming skill and experience (e.g., nation enables the user to become more aware, knowledge of ML models, built-in methods, make judgment about the correctness of the see Fig 1). Moreover, we might be able to output and mechanism; it also supports in- build transparent data science tools using these terpretability, accountability of algorithmic de- explainers, however, we cannot apply them cision making action [2]. Transparency and for designing transparent news feed or sociointerpretability are related through explana- technical systems (e.g., transparent twitter), tion, these relationships are shown in Figure because most of these news feed uses propri2. The way existing interpretability tool works etary algorithm [40]. Research also showed is also through explanation [18]. Explana- that explanation may enhance user’s positive attitude towards a system, but not necessarily trust [7]. These limitations encouraged us to discover a distinct way of designing algorithmic transparency at the interface level.

Thus, in this study, we propose a cognitive style based approach through incorporating tinkering ability into the design. 2.3. Tinkering proposed that efective tinkering happens when it is associated with pause and reflection about software features. We applied tinkering to design transparent algorithmic system with the hope that its exploratory nature will make the overall algorithmic transparency experience less overwhelming. Informed by several existing research [ 28, 30, 49, 50 ], the association of gender with respect to tinkering cannot be overlooked, discussed below.

Tinkering is a cognitive style or a “mindset” to approach problem-solving through “experimentation and discovery”, [43]; it is associ- 2.3.1. Tinkering and Gender ated with exploratory behavior, trial and error method, deviation from instructions when Previous research has identified gender diflearning [44]. Tinkering is an act of playful ferences in the tinkering attitude [ 30, 44, 28 ], experimentation that enhances motivation, in- and confirmed that females tend to tinker or lfuence learning, innovation [ 45, 44 ], impact explore new software features (e.g., spreadtask completion and performance [46, 47, 30]. sheet) less compared to the males for problemEven though tinkering is often associated with solving software [30], also in Computer Scimaking activities under playful conditions [48], ence education (e.g., programming assignment) tinkering behavior has shown to improve learn- [44]. Numerous studies have showed that tining and educational benefits in domains such kering is a mental or psychological trait that as engineering, robots, and programming (e.g., distinguishes how diferent genders (males and debugging, block-based) [48, 30, 46]. How- females) approach a given task (e.g., making ever, tinkering on its own may [ 44, 48, 45 ] or an Arduino project) [ 44, 47, 28, 30, 48 ]; tinmay not be a beneficial strategy for problem- kering is also one of the facets of gender-inclusive solving [30], for example, Beckwith et al. [30] design [49]. Gender-inclusiveness [49] design do not suggest building a diferent ver- transparent UI design, followed by feature desion of the same software for a diferent group scription, and a brief discussion of complete of user [ 28 ], rather, it advocates for designs transparent news feed prototype, Glass News that support diferent gender groups equally Feed. Finally, we show how tinkering based [51]. Gender inclusivity relies upon five facets approach can be applied to determine how of gender diferences: motivations, computer much algorithmic transparency is desired across self-eficacy, tinkering, information process- diferent user groups, which essentially helps ing style, risk aversion, that can impact the in the determination of gender diferences in use of problem solving software. While “In- the interface design. clusive Design considers the full range of human diversity with respect to ability, language, 3.1. Tinkering and Transparent culture, gender, age, and other forms of hu- Algorithmic User Interfaces man diference.” [52], gender is one aspect of inclusive design. Informed and inspired Transparent algorithmic UI’s primary objecby previous research [ 51, 34, 30, 28 ], in this tive is to reveal how it works by – explaining work, we will focus on only gender inclusive- the mechanism it uses to produce an outcome ness. [2]. Even though previous research suggests

In this study, we discuss tinkering as a means design guidelines for them, however, they did of designing transparent algorithmic UI’s, be- not addressed the cognitive aspects as a decause of it’s inherent exploratory nature might sign element in the UI design [8, 27, 13]. We be less overwhelming [13] to the user while decided to investigate this gap by proposing providing personalized user experience; tin- tinkering based transparent algorithmic UI (see kering also adds an additional ability in the Figure 2). Tinkering is not only related to design to detect gender diferences in the de- problem-solving but it is also associated with sign. Detecting gender issues early on dur- decision making [ 28 ], with regards to softing the design process improves the usabil- ware feature (e.g., new or existing) exploration; ity of the software for everyone, including thus, it allows us with the ability to measure marginalized users [ 28, 30 ]. algorithmic transparency needs (how much) across diverse population at the UI level. Following Beckwith et al. [30], we applied the 3. Designing Transparent term tinkering as users exploratory behavAlgorithmic User ioral action and practice with software, here news feed features. Allowing the user to “playInterface (UI) Through fully experiment” with the transparent algoTinkering rithmic features serves two potential purposes: ifrst, the design provides algorithmic inforTransparent algorithmic system for various mation in a manner that is not overwhelming interactive domain applications will work dif- to the user while providing personalized inferently; not only at the user interface level teractive experience; second, tinkering-based but also at the algorithmic level. For simplic- design has the ability to be tested for gender ity of design and illustration, we focused on inclusiveness issues. only a single interactive domain, the Facebook news feed. We first provide the rationale behind designing tinkering approach to

3.2. Case Study: Facebook Glass

News Feed

Glass News Feed Algorithm Features: Facebook Facebook is one of the most widely used socio- news feed algorithm applies users past action technical systems. Undoubtedly, Facebook has and behavior data to provide content. Even opened numerous opportunities for work, busi- though existing Fecebook news feed provides ness, collaboration and communication by con- certain amount of very high-level control about necting people worldwide; nonetheless, it has what the user sees and why (e.g., sort, hide, also caused various problems ranging from block, follow/unfollow, limited profile) [40], privacy threats, mental illness, addiction, to however, a transparent news feed requires other users trust violation. Facebook news feed has non-trivial control, which revolves around anbeen well studied in the literature for users swering “how” question in addition to answerperception and understanding of news feed ing “what” and “why”, but, Facebook news transparency [2, 40, 41]. Facebook news feed feed blog does not explain that very clearly works by allowing users to share content and [41]. For simplicity, we turned users actions consume content through automated selec- in the news feed into transparent algorithmic tion and ranking algorithm. The news feed interface feature (see Figure 3); for example, provides content that are relevant, interest- i) counts such as like and reaction count (e.g., ing, informative, having high quality [41]. Usershappy, love) in photos, status, videos, ii) list are usually unaware of how the underlying such as friends list, family, acquaintance, and algorithmic curation works [2, 53, 41]. There- iii) other features such as liked pages (e.g., fore, as a case study, we turned our attention product, business), public groups user follow, to design transparent algorithmic news feed [41], including descriptive features such as using a tinkering based approach. notes, tags can used as features. The real future transparent application might apply a different set of features in various categories.

We also enabled the ability for the user to be able to create their own feature set and explore the news feed outcome. We showed ing capability in the design through incoronly some of these features in the proposed porating Facebook data as interface features prototype. (see Figure 3); these features can be frequently turned on and of by the user for exploration,

Tinkering Capability: We enabled tinker- as described in [ 30, 28 ]. Each of the features can be in one of the states: i) when checked, design the exploration window in many difmarked by ✔, meaning feature selected for ferent ways, for diferent applications. current exploration, ii) when un-checked, in- The design of tinkering enabled transpardicated by an empty box, meaning not cur- ent algorithmic UI was inspired by the design rently under exploration, and iii) a question techniques suggested in problem-solving domark (?) to provide feature-related explana- main [30]. We added tinkering capabilities in tion [40]. These capabilities are hidden un- the Glass news feed design for feature set exder the drop down menu, this button is ac- ploration and experiment with correspondtivated when clicked, otherwise, it remains ing news feed output. The Glass news feed inactive to make sure that these extra abil- feature sets were derived from relevant reities does not overwhelm the user. Tinker- search [41], and was kept to a minimum numing count for any particular user can be mea- ber to avoid causing information overload. We sured by simply counting the number of fea- incorporated the ability to add a “user-defined” tures that were turned on and of during a feature set to provide some flexibility. The session. entire interactive experience is built on the concept of “playful experimentation” while

Subtle Explanation: Transparency cannot giving users enough control without hurting be implemented without providing some kind their interface experience [13]. of explanation. Thus, inspired by Rader et al. The resulting news feed is displayed on the [2], we subtly added “How” explanation. “How”news feed with confidence or accuracy inforexplanation, “Informs participants that the rank-mation (top right corner in Figure 4). The aling algorithm uses data collected about users gorithmic outcome (news feed after refresh) and their behaviors to calculate score score intentionally provides minimal information for each story”. Explanation “How” was in- such as confidence accuracy, because we have dicated by a question (?) mark, and gets ac- no idea what specific selection or ranking altivated when clicked to indicate more infor- gorithm Facebook originally uses for news mation (see Fig 3), by showing other meta- feed curation [41]. For similar reason, we did data information about the queried feature. not apply visualization, however, it is a posThis explanation feature becomes really es- sibility [18, 5, 13]. This is again our very first sential when user creates their own “user- trying of tinkering approach to achieve algodefined” feature set for experimentation with rithmic transparency in interactive systems. the news feed. This ability of defining userdefined feature set ensures enough flexibility 3.2.3. Measuring Gender Diferences in for exploration without overwhelming the user Glass News Feed with all possible tinkering options. 3.2.2. Transparent Glass News Feed The complete very first prototype of Glass news feed is presented in Figure 4. Tinkering or feature set exploration window is depicted on the left, and the corresponding outcome is shown on the right. For simplicity, we assumed that the features will appear on the news feed itself, though, it is possible to

Though, our main motivation for applying tinkering approach to design transparent algorithmic systems was to enable the exploratory nature of tinkering to unfold in the interface design, we suspect that the playful cognitive style might also be able to reduce cognitive load in the transparent systems [20, 15]. Another direct outcome from applying tinkering approach is that it allows the designer to check for gender issues in the design. The way our proposal is able to detect and mea- limited, because Facebook news feed uses prosure gender diferences is through measur- prietary algorithm [40]. A useful workaround ing (counting) “how much” tinkering (on/of) suggested in [2] can be beneficial for designan user engaged during an episode, consis- ing other socio-technical transparent systems, tent with prior study of tinkering in problem- by content analysis of blog posts or related solving [30] domain. Similarly, whether our sources. Second, we proposed transparent aldesign sufers from gender issues or not can gorithmic prototype for social media news feed be measured by collecting users tinkering fre- only, there are other algorithmic domain apquency, tinkering episode and tinkering rate. plications such as recommender systems, data For any particular task (in a user study), i) tin- science tools, data journalism tools, that can kering frequency is the number of features be designed and tested using similar strategy a user have turned on and of; ii) tinkering suggested in this study. Our design was also episode can be defined as a fixed amount of very limited in features and capabilities. Futime for task completion; iii) tinkering rate is ture work might take our design concept, exthe ratio of the previous two measures (i and pand (features/matrics) it, and test with the ii). Depending on the number of user groups various users to see how tinkering plays out taking part in the study, tinkering measures in achieving transparency. Third, we addressed for each user groups can be passed to sta- tinkering approach to the design of transpartistical or ML models for quantitative anal- ent algorithmic system, however, there are ysis. We did not show these measures in this other facets of cognitive styles such as riskstudy, rather, these are some of the potential aversion, information processing style (e.g., areas for future exploration. Transparency is [49, 34]) which might influence the use of transcritical for designing interactive social media parent systems (especially for females), we news feed for trust building and system ac- did not address these complex relationships ceptance. However, too much openness may while designing our proposal. Thus, future make the system vulnerable to various kinds work should examine other cognitive styles of exploitation, harm, and misuse. Thus, how of problem solving and their influence on tinto balance such competing, yet a necessary kering when designing transparent algorithaspect of a transparent news feed requires mic system. Additionally, most previous studfurther inquiry. ies investigated genders (males and females) influence in design research, thus, we need to expand our understanding by including marginal4. Limitations and Future ized LGBTQ+ communities in our design proWork cess. Finally, gender is one dimension in the broad spectrum of inclusive design [52], thus, future studies should investigate other diversity dimensions (e.g., race, class, language) while designing transparent systems.

In this study, we proposed a tinkering based approach towards designing transparent algorithmic user interface. There are several limitations to this study that is worth mentioning. First, the Glass news feed design was inspired by relevant research in Facebook news 5. Conclusion feed [41] and tinkering [ 30, 28 ]. While background research related to tinkering was broad and detailed, Facebook news feed research was

The demand for transparent algorithmic user interfaces is on the rise. Previous research applied explanations associated with text and

6. Acknowledgments

I would like to thank anonymous reviewers for their valuable comments and feedback. visualization techniques to improve the interpretability of ML models. These specialized tools are mainly used by technical experts such as data scientists and cannot be easily adapted for developing other transparent domain applications such as socio-technical systems. Furthermore, sample transparent UI prototypes in diverse domains exists, however, we do not know how to design a transparent interactive Facebook news feed that do not hurt the UX. Also, how much transparency is even desired across diverse population and how to measure that is also unknown. Thus, in this study, we proposed a very first tinkering based transparent algorithmic Glass News Feed UI prototype with the potential to navigate these multiple scenarios. This proposal can be easily expanded and adapted to design transparent algorithmic systems in various domain applications (e.g., transparent algorithmic tools for the journalists [54]), which essentially requires further examination with various groups of users to understand its technical feasibility, ethical and societal implications (e.g., benefits, harms). [10] K. Balog, F. Radlinski, S. Arakelyan, URL: https://docs.microsoft.com/ Transparent, scrutable and explainable en-us/azure/machine-learning/ user models for personalized recom- concept-responsible-ml, accessed: mendation, in: Proceedings of the 42nd 2020-11-12.

International ACM SIGIR Conference [19] R. Iyer, Y. Li, H. Li, M. Lewis, R. Sunon Research and Development in Infor- dar, K. Sycara, Transparency and exmation Retrieval, 2019, pp. 265–274. planation in deep reinforcement learn[11] M. Kay, S. Haroz, S. Guha, P. Dragicevic, ing neural networks, in: Proceedings of C. Wacharamanotham, Moving trans- the 2018 AAAI/ACM Conference on AI, parent statistics forward at chi, in: Pro- Ethics, and Society, 2018, pp. 144–150. ceedings of the 2017 CHI Conference [20] U. Ehsan, Q. V. Liao, M. Muller, Extended Abstracts on Human Factors M. O. Riedl, J. D. Weisz, Expanding in Computing Systems, 2017, pp. 534– explainability: Towards social trans541. parency in ai systems, arXiv preprint [12] T. Kulesza, S. Stumpf, M. Burnett, W.- arXiv:2101.04719 (2021).

K. Wong, Y. Riche, T. Moore, I. Oberst, [ 21 ] S. R. Hong, J. Hullman, E. Bertini, A. Shinsel, K. McIntosh, Explanatory Human factors in model interpretabildebugging: Supporting end-user de- ity: Industry practices, challenges, and bugging of machine-learned programs, needs, Proceedings of the ACM on in: 2010 IEEE Symposium on Visual Human-Computer Interaction 4 (2020) Languages and Human-Centric Com- 1–26.

puting, IEEE, 2010, pp. 41–48. [22] H. Nori, S. Jenkins, P. Koch, R. Caruana, [13] T. Kulesza, M. Burnett, W.-K. Wong, Interpretml: A unified framework for S. Stumpf, Principles of explanatory de- machine learning interpretability, arXiv bugging to personalize interactive ma- preprint arXiv:1909.09223 (2019). chine learning, in: Proceedings of the [23] J. Wexler, M. Pushkarna, T. Bolukbasi, 20th international conference on intelli- M. Wattenberg, F. Viégas, J. Wilson, gent user interfaces, 2015, pp. 126–137. The what-if tool: Interactive probing of [14] B. Kovach, T. Rosenstiel, The elements machine learning models, IEEE transof journalism: What newspeople should actions on visualization and computer know and the public should expect, graphics 26 (2019) 56–65.

Three Rivers Press (CA), 2014. [24] Z. C. Lipton, The mythos of model in[15] N. Diakopoulos, M. Koliska, Algorith- terpretability, Queue 16 (2018) 31–57. mic transparency in the news media, [25] R. Guidotti, A. Monreale, S. Ruggieri, Digital Journalism 5 (2017) 809–828. F. Turini, F. Giannotti, D. Pedreschi, A [16] C. D’Ignazio, L. F. Klein, Data feminism, survey of methods for explaining black

MIT Press, 2020. box models, ACM computing surveys [17] T. Gebru, J. Morgenstern, B. Vecchione, (CSUR) 51 (2018) 1–42.

J. Wortman Vaughan, H. Wallach, [26] H. Kaur, H. Nori, S. Jenkins, R. Caruana, H. Daumé III, K. Crawford, Datasheets H. Wallach, J. Wortman Vaughan, Infor datasets, 2018. URL: https: terpreting interpretability: Understand//www.microsoft.com/en-us/research/ ing data scientists’ use of interpretabilpublication/datasheets-for-datasets/. ity tools for machine learning, in: Pro[18] M. 2020, What is responsible ma- ceedings of the 2020 CHI Conference on chine learning? (preview), 2020. Human Factors in Computing Systems,

References

2020 , pp. 1 - 14 . and Trends in Human-Computer Inter[27] C.-H. Tsai , P. Brusilovsky , Designing action 13 ( 2020 ) 1 - 69 .

explanation interfaces for transparency [35] S. U. Noble , Algorithms of oppression:

and beyond ., in: IUI Workshops , 2019 . How search engines reinforce racism , [28] M. Burnett , S. Wiedenbeck , V. Grigore- nyu Press, 2018 .

anu , N. Subrahmaniyan , L. Beckwith, [36] S. Ballard , K. M. Chappell , K. Kennedy,

the 4th international workshop on End- surface ethical concerns related to tech-

user software engineering , 2008 , pp. nology , in: Proceedings of the 2019 on

21- 24 . Designing Interactive Systems Confer[29] J. Meyers-Levy , Gender diferences in ence, 2019 , pp. 421 - 433 .

information processing: A selectivity [37] M. Muller , M. Feinberg , T. George , S. J.

ern University, 1986 . Human-centered study of data science [30] L. Beckwith , C. Kissinger , M. Burnett, work practices , in: Extended Abstracts

S. Wiedenbeck , J. Lawrance , A . Black- of the 2019 CHI Conference on Human

well , C. Cook, Tinkering and gender in Factors in Computing Systems , 2019 ,

end-user programmers' debugging , in: pp. 1 - 8 .

Proceedings of the SIGCHI conference [38] B. Haibe-Kains , G. A. Adam , A . Hosny,

tems , 2006 , pp. 231 - 240 . C. McIntosh , A. Goldenberg , A . Kun[31] J. Kemper , D. Kolkman , Transparent daje, C. S. Greene , et al., Transparency

ity without a critical audience, Infor- gence , Nature 586 ( 2020 ) E14 - E16 .

mation , Communication & Society 22 [39] A. Meijer , Understanding modern

( 2019 ) 2081 - 2096 . transparency, International Review of [32] M. T. Ribeiro , S. Singh , C. Guestrin , Administrative Sciences 75 ( 2009 ) 255 -

"why should i trust you?" explaining 269.

the predictions of any classifier , in: [40] E. Rader , R. Gray , Understanding user

Proceedings of the 22nd ACM SIGKDD beliefs about algorithmic curation in the

discovery and data mining , 2016 , pp. of the 33rd annual ACM conference on

1135- 1144 . human factors in computing systems , [33] M. M. Burnett , E. F. Churchill , M. J. Lee , 2015 , pp. 173 - 182 .

Sig: gender-inclusive software: What [41] K. Cotter , J. Cho , E. Rader, Explaining

ceedings of the 33rd Annual ACM Con- the" news feed fyi" blog , in: Proceedings

ference Extended Abstracts on Human of the 2017 CHI conference extended

Factors in Computing Systems , 2015 , abstracts on human factors in comput-

pp. 857 - 860 . ing systems, 2017 , pp. 1553 - 1560 . [34] S. Stumpf , A. Peters , S. Bardzell , M. Bur- [42] S. M. Lundberg , S.-I. Lee , A unified

sign: A conceptual review , Foundations mation processing systems , 2017 , pp.

4765- 4774 . ing style, self-eficacy, and tinkering for [43] D. V. Loertscher , Invent to learn: Mak- robot tele-operation , in: 2018 15th In-

classroom , Teacher Librarian 41 ( 2013 ) Robots (UR) , IEEE, 2018 , pp. 443 - 448 .

45. [51] M. Burnett , Doing inclusive design: [44] S. Krieger , M. Allen , C. Rawn , Are fe- From gendermag in the trenches to in-

science? , in: Proceedings of the 46th Proceedings of the International Con-

puter Science Education , 2015 , pp. 102 - 2020 , pp. 1 - 6 .

107. [52] idrc, Inclusive design research center, [45] M. G. Jones , L. Brader-Araje , L. W. Car- 1975. URL: https://idrc.ocadu.ca/, ac-

boni , G. Carter, M. J. Rua , E. Banilower, cessed: 2021 -10-02.

H. Hatch , Tool time: Gender and stu- [53] M. A. DeVito , J. Birnholtz, J. T. Hancock,

in Science Teaching 37 ( 2000 ) 760 - 783 . 2018 CHI conference on human factors [46] Y. Dong , S. Marwan , V. Catete , T. Price, in computing systems, 2018 , pp. 1 - 12 .

T. Barnes , Defining tinkering behavior [54] D. Showkat , E. P. S. Baumer , Outliers:

in open-ended block-based program- More than numbers? ( 2020 ).

the 50th ACM Technical Symposium on

Computer Science Education , 2019 , pp.

1204- 1210 . [47] M. U. Bers , L. Flannery , E. R. Kazakof ,

puters & Education 72 ( 2014 ) 145 - 157 . [48] M. H. Lamers , F. J. Verbeek , P. W.

ment Technology , Springer, 2013 , pp.

568- 571 . [49] M. Burnett , S. Stumpf , J. Macbeth,

Computers 28 ( 2016 ) 760 - 787 . [50] D. Showkat , C. Grimm , Identifying gen-