Transparency and Trust in Human-AI-Interaction: The Role of Model-Agnostic Explanations in Computer Vision-Based Decision Support

Meske, Christian; Bunde, E

doi:10.1007/978-3-030-50334-5_4

Cited by 52 publications

(39 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…XAI has already been applied in different contexts such as health sector [26] or applications in the context of recommender systems [27]. The reasons and motivations for the use of XAI can be described as, for example, explain to justify, control, improve, discover, verify, or manage as well as to comply to legislation [5,28].…”

Section: Deep Learning Algorithms As Black Boxesmentioning

confidence: 99%

AI-Assisted and Explainable Hate Speech Detection for Social Media Moderators – A Design Science Approach

Bunde¹

2021

Proceedings of the Annual Hawaii International Conference on System Sciences

Self Cite

View full text Add to dashboard Cite

To date, the detection of hate speech is still primarily carried out by humans, yet there is great potential for combining human expertise with automated approaches. However, identified challenges include low levels of agreement between humans and machines due to the algorithms' missing expertise of, e.g., cultural, and social structures. In this work, a design science approach is used to derive design knowledge and develop an artifact, through which humans are integrated in the process of detecting and evaluating hate speech. For this purpose, explainable artificial intelligence (XAI) is utilized: the artifact will provide explanative information, why the deep learning model predicted whether a text contains hate. Results show that the instantiated design knowledge in form of a dashboard is perceived as valuable and that XAI features increase the perception of the artifact's usefulness, ease of use, trustworthiness as well as the intention to use it.

show abstract

Section: Deep Learning Algorithms As Black Boxesmentioning

confidence: 99%

AI-Assisted and Explainable Hate Speech Detection for Social Media Moderators – A Design Science Approach

Bunde¹

2021

Proceedings of the Annual Hawaii International Conference on System Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…In making decisions between models, it supported both expert and non-expert users while evaluating their confidence and improving untrustworthy models by providing insight into their predictions. Further, in [1], the authors address the effect of explainability on trust in AI and computer vision systems through the improved understandability and predictability of deep learning-based computer vision decisions on medical diagnostic data. They also explore how XAI can be used to compare the recognition techniques of two deep learning models: Multi-Layer Perceptron and Convolutional Neural Network (CNN).…”

Section: Explainable Artificial Intelligence In the Medical Fieldmentioning

confidence: 99%

“…On the other hand, in recent years, deep learning and AI-based extraction of information from images have received growing interest in fields such as medical diagnostics, finance, forensics, scientific research and education. In these domains, it is often necessary to understand the reason for the model's decisions so that the human can validate the decision's outcome [1].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Explainable Artificial Intelligence for Human Decision Support System in the Medical Domain

Knapič

Malhi

Saluja

et al. 2021

MAKE

View full text Add to dashboard Cite

In this paper, we present the potential of Explainable Artificial Intelligence methods for decision support in medical image analysis scenarios. Using three types of explainable methods applied to the same medical image data set, we aimed to improve the comprehensibility of the decisions provided by the Convolutional Neural Network (CNN). In vivo gastral images obtained by a video capsule endoscopy (VCE) were the subject of visual explanations, with the goal of increasing health professionals’ trust in black-box predictions. We implemented two post hoc interpretable machine learning methods, called Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP), and an alternative explanation approach, the Contextual Importance and Utility (CIU) method. The produced explanations were assessed by human evaluation. We conducted three user studies based on explanations provided by LIME, SHAP and CIU. Users from different non-medical backgrounds carried out a series of tests in a web-based survey setting and stated their experience and understanding of the given explanations. Three user groups (n = 20, 20, 20) with three distinct forms of explanations were quantitatively analyzed. We found that, as hypothesized, the CIU-explainable method performed better than both LIME and SHAP methods in terms of improving support for human decision-making and being more transparent and thus understandable to users. Additionally, CIU outperformed LIME and SHAP by generating explanations more rapidly. Our findings suggest that there are notable differences in human decision-making between various explanation support settings. In line with that, we present three potential explainable methods that, with future improvements in implementation, can be generalized to different medical data sets and can provide effective decision support to medical experts.

show abstract

“…In this paper, we use two post hoc model agnostic explainability techniques called Local Interpretable Modelagnostic Explanations (LIME) [15,16] and Shapley Additive exPlanations (SHAP) [17,18] to analyze the models on the dataset by checking the evaluation metrics and select the model where explanation can be separated from the models. The intent is to evaluate the black-box model much easily on how each word plays an important role in the prediction of the sarcastic dialogues by the speaker using the sequential nature of a scene in the TV series.…”

Section: Introductionmentioning

confidence: 99%

Explainable Artificial Intelligence for Sarcasm Detection in Dialogues

Kumar

Dikshit

Albuquerque

2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Sarcasm detection in dialogues has been gaining popularity among natural language processing (NLP) researchers with the increased use of conversational threads on social media. Capturing the knowledge of the domain of discourse, context propagation during the course of dialogue, and situational context and tone of the speaker are some important features to train the machine learning models for detecting sarcasm in real time. As situational comedies vibrantly represent human mannerism and behaviour in everyday real-life situations, this research demonstrates the use of an ensemble supervised learning algorithm to detect sarcasm in the benchmark dialogue dataset, MUStARD. The punch-line utterance and its associated context are taken as features to train the eXtreme Gradient Boosting (XGBoost) method. The primary goal is to predict sarcasm in each utterance of the speaker using the chronological nature of a scene. Further, it is vital to prevent model bias and help decision makers understand how to use the models in the right way. Therefore, as a twin goal of this research, we make the learning model used for conversational sarcasm detection interpretable. This is done using two post hoc interpretability approaches, Local Interpretable Model-agnostic Explanations (LIME) and Shapley Additive exPlanations (SHAP), to generate explanations for the output of a trained classifier. The classification results clearly depict the importance of capturing the intersentence context to detect sarcasm in conversational threads. The interpretability methods show the words (features) that influence the decision of the model the most and help the user understand how the model is making the decision for detecting sarcasm in dialogues.

show abstract

Transparency and Trust in Human-AI-Interaction: The Role of Model-Agnostic Explanations in Computer Vision-Based Decision Support

Cited by 52 publications

References 44 publications

AI-Assisted and Explainable Hate Speech Detection for Social Media Moderators – A Design Science Approach

AI-Assisted and Explainable Hate Speech Detection for Social Media Moderators – A Design Science Approach

Explainable Artificial Intelligence for Human Decision Support System in the Medical Domain

Explainable Artificial Intelligence for Sarcasm Detection in Dialogues

Contact Info

Product

Resources

About