More Like this

1. The Impacts of Referent Display on Gesture and Speech Elicitation

   https://doi.org/10.1109/TVCG.2022.3203090  

   Williams, Adam S.; Ortega, Francisco R. (July 2022, IEEE Transactions on Visualization and Computer Graphics)

   Elicitation studies have become a popular method of participatory design. While traditionally used to examine unimodal gesture interactions, elicitation has started being used with other novel interaction modalities. Unfortunately, there has been no work that examines the impact of referent display on elicited interaction proposals. To address that concern this work provides a detailed comparison between two elicitation studies that were similar in design apart from the way that participants were prompted for interaction proposals (i.e., the referents). Based on this comparison the impact of referent display on speech and gesture interaction proposals are each discussed. The interaction proposals between these elicitation studies were not identical. Gesture proposals were the least impacted by referent display, showing high proposal similarity between the two works. Speech proposals were highly biased by text referents with proposals directly mirroring text-based referents an average of 69.36% of the time. In short, the way that referents are presented during elicitation studies can impact the resulting interaction proposals; however, the level of impact found is dependent on the modality of input elicited. 

   more » « less
2. Towards Establishing Consistent Proposal Binning Methods for Unimodal and Multimodal Interaction Elicitation Studies

   https://doi.org/10.1007/978-3-031-05311-5  

   Xiaoyan Zhou, Adam S. (June 2022, HCII: International Conference on Human-Computer Interaction)

   The Open University of Japan, Chiba (Ed.)

   More than two hundred papers on elicitation studies have been published in the last ten years. These works are mainly focused on generating user-defined gesture sets and discovering natural feeling multimodal interaction techniques with virtual objects. Few papers have discussed binning the elicited interaction proposals after data collection. Binning is a process of grouping the entire set of user-generated interaction proposals based on similarity criteria. The binned set of proposals is then analyzed to produce a consensus set, which results in the user-defined interaction set. This paper presents a formula to use when deciding how to bin interaction proposals, thus helping to establish a more consistent binning procedure. This work can provide human-computer interaction (HCI) researchers with the guidance they need for interaction elicitation data processing, which is largely missing from current elicitation study literature. Using this approach will improve the efficiency and effectiveness of the binning process, increase the reliability of us er-defined interaction sets, and most importantly, improve the replicability of elicitation studies. 

   more » « less
3. Understanding Gesture and Speech Multimodal Interactions for Manipulation Tasks in Augmented Reality Using Unconstrained Elicitation

   https://doi.org/10.1145/3427330  

   Williams, Adam S.; Ortega, Francisco R. (November 2020, Proceedings of the ACM on Human-Computer Interaction)

   null (Ed.)

   This research establishes a better understanding of the syntax choices in speech interactions and of how speech, gesture, and multimodal gesture and speech interactions are produced by users in unconstrained object manipulation environments using augmented reality. The work presents a multimodal elicitation study conducted with 24 participants. The canonical referents for translation, rotation, and scale were used along with some abstract referents (create, destroy, and select). In this study time windows for gesture and speech multimodal interactions are developed using the start and stop times of gestures and speech as well as the stoke times for gestures. While gestures commonly precede speech by 81 ms we find that the stroke of the gesture is commonly within 10 ms of the start of speech. Indicating that the information content of a gesture and its co-occurring speech are well aligned to each other. Lastly, the trends across the most common proposals for each modality are examined. Showing that the disagreement between proposals is often caused by a variation of hand posture or syntax. Allowing us to present aliasing recommendations to increase the percentage of users' natural interactions captured by future multimodal interactive systems. 

   more » « less
4. Quantifying 60 Years of Gender Bias in Biomedical Research with Word Embeddings

   https://doi.org/10.18653/v1/2020.bionlp-1.1  

   Rios, Anthony; Joshi, Reenam; Shin, Hejin (July 2020, Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing)

   Gender bias in biomedical research can have an adverse impact on the health of real people. For example, there is evidence that heart disease-related funded research generally focuses on men. Health disparities can form between men and at-risk groups of women (i.e., elderly and low-income) if there is not an equal number of heart disease-related studies for both genders. In this paper, we study temporal bias in biomedical research articles by measuring gender differences in word embeddings. Specifically, we address multiple questions, including, How has gender bias changed over time in biomedical research, and what health-related concepts are the most biased? Overall, we find that traditional gender stereotypes have reduced over time. However, we also find that the embeddings of many medical conditions are as biased today as they were 60 years ago (e.g., concepts related to drug addiction and body dysmorphia). 

   more » « less
5. Enhancing Image Classification Capabilities of Crowdsourcing-Based Methods through Expanded Input Elicitation

   Yasmin, Romena; Grassel, Joshua T.; Hassan, Md Mahmudulla; Fuentes, Olac; Escobedo, Adolfo R. (November 2021, Proceedings of the Ninth AAAI Conference on Human Computation and Crowdsourcing (HCOMP2021))

   Kamar, Ece; Luther, Kurt (Ed.)

   This study investigates how different forms of input elicitation obtained from crowdsourcing can be utilized to improve the quality of inferred labels for image classification tasks, where an image must be labeled as either positive or negative depending on the presence/absence of a specified object. Three types of input elicitation methods are tested: binary classification (positive or negative); level of confidence in binary response (on a scale from 0-100%); and what participants believe the majority of the other participants’ binary classification is. We design a crowdsourcing experiment to test the performance of the proposed input elicitation methods and use data from over 200 participants. Various existing voting and machine learning (ML) methods are applied and others developed to make the best use of these inputs. In an effort to assess their performance on classification tasks of varying difficulty, a systematic synthetic image generation process is developed. Each generated image combines items from the MPEG-7 Core Experiment CE-Shape-1 Test Set into a single image using multiple parameters (e.g., density, transparency, etc.) and may or may not contain a target object. The difficulty of these images is validated by the performance of an automated image classification method. Experimental results suggest that more accurate classifications can be achieved when using the average of the self-reported confidence values as an additional attribute for ML algorithms relative to what is achieved with more traditional approaches. Additionally, they demonstrate that other performance metrics of interest, namely reduced false-negative rates, can be prioritized through special modifications of the proposed aggregation methods that leverage the variety of elicited inputs. 

   more » « less