The effects of example-based explanations in a machine learning interface

Cai, Carrie J.; Jongejan, Jonas; Holbrook, Jess

doi:10.1145/3301275.3302289

Cited by 150 publications

(100 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research on how to reduce over-trust effect suggested different solutions, but it needs more investigation to measure and adjust the relationship between different variable including trust, certainty level, cognitive styles, personality and liability. Existing proposals revolve around comparative explanations [13], argumentation [20], personalised explanation based on user personality [75], uncertainty and error presentation [76]. Research is still needed to investigate how to embed these solutions in the interfaces considering other usability and user experience factors such as the timing, the level of details, the feedback to collect from end-users and the evolution of explanation to reflect it.…”

Section: Reported Risksmentioning

confidence: 99%

Explainable Recommendations in Intelligent Systems: Delivery Methods, Modalities and Risks

Naiseh

Jiang

et al. 2020

Research Challenges in Information Science

View full text Add to dashboard Cite

With the increase in data volume, velocity and types, intelligent human-agent systems have become popular and adopted in different application domains, including critical and sensitive areas such as health and security. Humans' trust, their consent and receptiveness to recommendations are the main requirement for the success of such services. Recently, the demand on explaining the recommendations to humans has increased both from humans interacting with these systems so that they make an informed decision and, also, owners and systems managers to increase transparency and consequently trust and users' retention. Existing systematic reviews in the area of explainable recommendations focused on the goal of providing explanations, their presentation and informational content. In this paper, we review the literature with a focus on two user experience facets of explanations; delivery methods and modalities. We then focus on the risks of explanation both on user experience and their decision making. Our review revealed that explanations delivery to end-users is mostly designed to be along with the recommendation in a push and pull styles while archiving explanations for later accountability and traceability is still limited. We also found that the emphasis was mainly on the benefits of recommendations while risks and potential concerns, such as over-reliance on machines, is still a new area to explore.

show abstract

Section: Reported Risksmentioning

confidence: 99%

Explainable Recommendations in Intelligent Systems: Delivery Methods, Modalities and Risks

Naiseh

Jiang

et al. 2020

Research Challenges in Information Science

View full text Add to dashboard Cite

show abstract

“…Hence, amplification systems also require high transparency [ 189 , 192 ]. To support algorithm transparency, amplification systems can show visual activation of features that led to the recommendation [ 9 ] or similar cases in the data that serve as evidence for the current recommendation [ 193 ]. Summarizing human decisions can involve expressing data transformations as natural language rules [ 4 , 28 ] and visual node-link diagrams [ 22 ].…”

Section: Taxonomy Of Expertise Amplificationmentioning

confidence: 99%

Amplifying Domain Expertise in Clinical Data Pipelines

2020

View full text Add to dashboard Cite

Digitization of health records has allowed the health care domain to adopt data-driven algorithms for decision support. There are multiple people involved in this process: a data engineer who processes and restructures the data, a data scientist who develops statistical models, and a domain expert who informs the design of the data pipeline and consumes its results for decision support. Although there are multiple data interaction tools for data scientists, few exist to allow domain experts to interact with data meaningfully. Designing systems for domain experts requires careful thought because they have different needs and characteristics from other end users. There should be an increased emphasis on the system to optimize the experts’ interaction by directing them to high-impact data tasks and reducing the total task completion time. We refer to this optimization as amplifying domain expertise. Although there is active research in making machine learning models more explainable and usable, it focuses on the final outputs of the model. However, in the clinical domain, expert involvement is needed at every pipeline step: curation, cleaning, and analysis. To this end, we review literature from the database, human-computer information, and visualization communities to demonstrate the challenges and solutions at each of the data pipeline stages. Next, we present a taxonomy of expertise amplification, which can be applied when building systems for domain experts. This includes summarization, guidance, interaction, and acceleration. Finally, we demonstrate the use of our taxonomy with a case study.

show abstract

“…We wanted the discussion on values to be grounded in a broad range of realistic examples based on the current capabilities of AI technologies. AI systems are notoriously opaque, making them difficult to understand and explain independent of examples [12]. The AI cards were created based on findings from a pilot, conducted with 5 journalism students.…”

Section: Value Cardsmentioning

confidence: 99%

AI should embody our values: Investigating journalistic values to inform AI technology design

Komatsu

Lopez

Makri

et al. 2020

Proceedings of the 11th Nordic Conference on Human-Computer Interaction: Shaping Experiences, Shaping Society

View full text Add to dashboard Cite

In the current climate of shrinking newsrooms and revenues, journalists face increasing pressures exerted by the industry's for-profit focus and the expectation of intensified output. While AI-enabled journalism has great potential to help alleviate journalists' pressures, it might also disrupt journalistic norms and, at worst, interfere with their duty to inform the public. For AI systems to be as useful as possible, designers should understand journalists' professional values and incorporate them into their designs. We report findings from interviews with journalists to understand their perceptions of how professional values that are important to them (such as truth, impartiality and originality) might be supported and/or undermined by AI technologies. Based on these findings, we provide design insight and guidelines for incorporating values into the design of AI systems. We argue HCI design can achieve the strongest possible value alignment by moving beyond merely supporting important values, to truly embodying them. CCS Human-centered computing Empirical studies in HCI.

show abstract

The effects of example-based explanations in a machine learning interface

Cited by 150 publications

References 25 publications

Explainable Recommendations in Intelligent Systems: Delivery Methods, Modalities and Risks

Explainable Recommendations in Intelligent Systems: Delivery Methods, Modalities and Risks

Amplifying Domain Expertise in Clinical Data Pipelines

AI should embody our values: Investigating journalistic values to inform AI technology design

Contact Info

Product

Resources

About