Amogh Joshi - Academia.edu (original) (raw)

Papers by Amogh Joshi

FDG '22: Proceedings of the 17th International Conference on the Foundations of Digital Games

Games are now ubiquitous, and educational games are becoming increasingly prevalent. Like other g... more Games are now ubiquitous, and educational games are becoming increasingly prevalent. Like other games, educational video games attract participants from different ethnicities and with different gender expressions. As such, educational game designers face a necessity to develop inclusive games. In this paper, we focus on inclusivity, diversity, and equity (DEI) issues by investigating if the computer programming game Mazzy benefited participants from broad demographic backgrounds. We highlight inclusive features present in Mazzy, and, focusing on the participants' self-reported gender and race/ethnicity, reflect on their play experience and learning outcomes. We found evidence that the game supported learning outcomes and facilitated an engaging play experience for participants from diverse demographic backgrounds. We discuss challenges and implications for the broader literature. CCS CONCEPTS • Human-centered computing → HCI design and evaluation methods.

arXiv (Cornell University), Oct 4, 2021

This paper investigates visual media shared by US national politicians on Twitter, how a politici... more This paper investigates visual media shared by US national politicians on Twitter, how a politician's variety of image types shared reflects their political position, and identifies a hazard in using standard methods for image characterization in this context. While past work has yielded valuable results on politicians' use of imagery in social media, that work has focused primarily on photographic media, which may not be sufficient given the variety of visual media shared in such spaces (e.g., infographics, illustrations, or memes). Leveraging three popular deep learning models to characterize politicians' visuals, this work uses clustering to identify eight types of visual media shared on Twitter, several of which are not photographic in nature. Results also show individual politicians share a variety of these types, and the distributions of their imagery across these clusters is correlated with their overall ideological position-e.g., liberal politicians appear to share a larger proportion of infographic-style images, and conservative politicians appear to share more patriotic imagery. At the same time, manual assessment reveals that these image characterization models group images with vastly different semantic meaning into the same clusters, as confirmed in a post-hoc analysis of hateful memetic imagery. These results suggest that, while image-characterization techniques do identify general types of imagery that correlate with political ideology, these methods miss critical semantic-and therefore politically relevant-differences among images. Consequently, care should be taken when dealing with the varieties of imagery shared in online spaces, especially in political contexts.

arXiv (Cornell University), Apr 13, 2022

This work advances investigations into the visual media shared by agents in disinformation campai... more This work advances investigations into the visual media shared by agents in disinformation campaigns by characterizing the images shared by accounts identified by Twitter as being part of such campaigns. Using images shared by US politicians' Twitter accounts as a baseline and training set, we build models for inferring the ideological presentation of accounts using the images they share. Results show that, while our models recover the expected bimodal ideological distribution of US politicians, we find that, on average, four separate influence campaigns-attributed to Iran, Russia, China, and Venezuela-all present conservative ideological presentations in the images they share. Given that prior work has shown Twitter accounts used by Russian disinformation agents are ideologically diverse in the text and news they share, these image-oriented findings provide new insights into potential axes of coordination and suggest these accounts may not present consistent ideological positions across modalities.

CHI Conference on Human Factors in Computing Systems

This work is licensed under a Creative Commons Attribution-Share Alike International 4.0 License.

The 16th International Conference on the Foundations of Digital Games (FDG) 2021, 2021

COVID-19 has upended lives everywhere, causing millions of deaths and tens of millions of infecti... more COVID-19 has upended lives everywhere, causing millions of deaths and tens of millions of infections worldwide. Nevertheless, for many people, staying in permanent isolation is neither desirable nor possible. To mitigate the spread of the disease, we iteratively developed a game that teaches hygienic best practices for preventing COVID-19. We consulted professional game designers, health experts, and educational technology designers. We then compared the effectiveness of the game to an equivalent video in two longitudinal experiments during the pandemic: 1) an experiment in a programming lab (N=11), and 2) an online-only experiment (N=475). In Experiment #1, we observe that participants in the game condition had higher intrinsic motivation, and a more sustained rise in hygienic self-efficacy, compared to participants in the video condition. Both conditions saw a rise in COVID-19 knowledge and positive hygienic attitude. Both conditions were relatively unchanged in COVID-19 anxiety and hygienic behavior. In Experiment #2, participants in the game condition experienced greater intrinsic motivation than participants in the video condition. Both conditions saw a sustained rise in COVID-19 hygienic self-efficacy, positive hygienic attitudes, and knowledge. Neither condition saw an effect on COVID-19 anxiety. Our work demonstrates that game-based learning can be an effective approach for teaching COVID-19 hygienic knowledge, for improving COVID-19 hygienic self-efficacy, and for fostering COVID-19 hygienic positive attitudes, and is more intrinsically motivating than video-based learning. This work is licensed under a Creative Commons Attribution-Share Alike International 4.0 License.

FDG '22: Proceedings of the 17th International Conference on the Foundations of Digital Games

Games are now ubiquitous, and educational games are becoming increasingly prevalent. Like other g... more Games are now ubiquitous, and educational games are becoming increasingly prevalent. Like other games, educational video games attract participants from different ethnicities and with different gender expressions. As such, educational game designers face a necessity to develop inclusive games. In this paper, we focus on inclusivity, diversity, and equity (DEI) issues by investigating if the computer programming game Mazzy benefited participants from broad demographic backgrounds. We highlight inclusive features present in Mazzy, and, focusing on the participants' self-reported gender and race/ethnicity, reflect on their play experience and learning outcomes. We found evidence that the game supported learning outcomes and facilitated an engaging play experience for participants from diverse demographic backgrounds. We discuss challenges and implications for the broader literature. CCS CONCEPTS • Human-centered computing → HCI design and evaluation methods.

arXiv (Cornell University), Oct 4, 2021

This paper investigates visual media shared by US national politicians on Twitter, how a politici... more This paper investigates visual media shared by US national politicians on Twitter, how a politician's variety of image types shared reflects their political position, and identifies a hazard in using standard methods for image characterization in this context. While past work has yielded valuable results on politicians' use of imagery in social media, that work has focused primarily on photographic media, which may not be sufficient given the variety of visual media shared in such spaces (e.g., infographics, illustrations, or memes). Leveraging three popular deep learning models to characterize politicians' visuals, this work uses clustering to identify eight types of visual media shared on Twitter, several of which are not photographic in nature. Results also show individual politicians share a variety of these types, and the distributions of their imagery across these clusters is correlated with their overall ideological position-e.g., liberal politicians appear to share a larger proportion of infographic-style images, and conservative politicians appear to share more patriotic imagery. At the same time, manual assessment reveals that these image characterization models group images with vastly different semantic meaning into the same clusters, as confirmed in a post-hoc analysis of hateful memetic imagery. These results suggest that, while image-characterization techniques do identify general types of imagery that correlate with political ideology, these methods miss critical semantic-and therefore politically relevant-differences among images. Consequently, care should be taken when dealing with the varieties of imagery shared in online spaces, especially in political contexts.

arXiv (Cornell University), Apr 13, 2022

This work advances investigations into the visual media shared by agents in disinformation campai... more This work advances investigations into the visual media shared by agents in disinformation campaigns by characterizing the images shared by accounts identified by Twitter as being part of such campaigns. Using images shared by US politicians' Twitter accounts as a baseline and training set, we build models for inferring the ideological presentation of accounts using the images they share. Results show that, while our models recover the expected bimodal ideological distribution of US politicians, we find that, on average, four separate influence campaigns-attributed to Iran, Russia, China, and Venezuela-all present conservative ideological presentations in the images they share. Given that prior work has shown Twitter accounts used by Russian disinformation agents are ideologically diverse in the text and news they share, these image-oriented findings provide new insights into potential axes of coordination and suggest these accounts may not present consistent ideological positions across modalities.

CHI Conference on Human Factors in Computing Systems

This work is licensed under a Creative Commons Attribution-Share Alike International 4.0 License.

The 16th International Conference on the Foundations of Digital Games (FDG) 2021, 2021

COVID-19 has upended lives everywhere, causing millions of deaths and tens of millions of infecti... more COVID-19 has upended lives everywhere, causing millions of deaths and tens of millions of infections worldwide. Nevertheless, for many people, staying in permanent isolation is neither desirable nor possible. To mitigate the spread of the disease, we iteratively developed a game that teaches hygienic best practices for preventing COVID-19. We consulted professional game designers, health experts, and educational technology designers. We then compared the effectiveness of the game to an equivalent video in two longitudinal experiments during the pandemic: 1) an experiment in a programming lab (N=11), and 2) an online-only experiment (N=475). In Experiment #1, we observe that participants in the game condition had higher intrinsic motivation, and a more sustained rise in hygienic self-efficacy, compared to participants in the video condition. Both conditions saw a rise in COVID-19 knowledge and positive hygienic attitude. Both conditions were relatively unchanged in COVID-19 anxiety and hygienic behavior. In Experiment #2, participants in the game condition experienced greater intrinsic motivation than participants in the video condition. Both conditions saw a sustained rise in COVID-19 hygienic self-efficacy, positive hygienic attitudes, and knowledge. Neither condition saw an effect on COVID-19 anxiety. Our work demonstrates that game-based learning can be an effective approach for teaching COVID-19 hygienic knowledge, for improving COVID-19 hygienic self-efficacy, and for fostering COVID-19 hygienic positive attitudes, and is more intrinsically motivating than video-based learning. This work is licensed under a Creative Commons Attribution-Share Alike International 4.0 License.