skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.


Title: MoodSmith: Enabling Mood-Consistent Multimedia for AI-Generated Advocacy Campaigns
Emotion is vital to information and message processing, playing a key role in attitude formation. Consequently, creating a mood that evokes an emotional response is essential to any compelling piece of outreach communication. Many nonprofits and charities, despite having established messages, face challenges in creating advocacy campaign videos for social media. It requires significant creative and cognitive efforts to ensure that videos achieve the desired mood across multiple dimensions: script, visuals, and audio. We introduce Mood- Smith, an AI-powered system that helps users explore mood possibilities for their message and create advocacy campaigns that are mood-consistent across dimensions. To achieve this, MoodSmith uses emotive language and plotlines for scripts, artistic style and color palette for visuals, and positivity and energy for audio. Our studies show that MoodSmith can effectively achieve a variety of moods, and the produced videos are consistent across media dimensions.  more » « less
Award ID(s):
2129020
PAR ID:
10543741
Author(s) / Creator(s):
; ;
Publisher / Repository:
ICCC'24 15th International Conference on Computational Creativity
Date Published:
Format(s):
Medium: X
Location:
Jönköping, Sweden
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    Dimensions of human mood, behaviour and vital signs cycle over multiple timescales. However, it remains unclear which dimensions are most cyclical, and how daily, weekly, seasonal and menstrual cycles compare in magnitude. The menstrual cycle remains particularly understudied because, not being synchronized across the population, it will be averaged out unless menstrual cycles can be aligned before analysis. Here, we analyse 241 million observations from 3.3 million women across 109 countries, tracking 15 dimensions of mood, behaviour and vital signs using a women’s health mobile app. Out of the daily, weekly, seasonal and menstrual cycles, the menstrual cycle had the greatest magnitude for most of the measured dimensions of mood, behaviour and vital signs. Mood, vital signs and sexual behaviour vary most substantially over the course of the menstrual cycle, while sleep and exercise behaviour remain more constant. Menstrual cycle effects are directionally consistent across countries. 
    more » « less
  2. Generating realistic audio for human actions is critical for applications such as film sound effects and virtual reality games. Existing methods assume complete correspondence between video and audio during training, but in real-world settings, many sounds occur off-screen or weakly correspond to visuals, leading to uncontrolled ambient sounds or hallucinations at test time. This paper introduces AV-LDM, a novel ambient-aware audio generation model that disentangles foreground action sounds from ambient background noise in in-the-wild training videos. The approach leverages a retrieval-augmented generation framework to synthesize audio that aligns both semantically and temporally with the visual input. Trained and evaluated on Ego4D and EPIC-KITCHENS datasets, along with the newly introduced Ego4D-Sounds dataset (1.2M curated clips with action-audio correspondence), the model outperforms prior methods, enables controllable ambient sound generation, and shows promise for generalization to synthetic video game clips. This work is the first to emphasize faithful video-to-audio generation focused on observed visual content despite noisy, uncurated training data. 
    more » « less
  3. Nature experiences, especially the visual aspects of nature, have been widely used to facilitate relaxation. Fueled by digital technology, simulated visual nature experiences have gained popularity in creating healing environments that induce relaxation. However, while easily applicable, not all nature-imitating visuals lead to relaxation. How to effectively design relaxing visual nature experiences remains largely unexplored. This paper investigates how different nature qualities facilitate relaxing visual experiences and the roles of two personal characteristics (mood and nature-relatedness) play. Through an online survey and interviews, we assessed 16 nature video clips, representing eight distinctive nature qualities, and compared perceived experiences while considering the influence of personal characteristics. The results indicate four types of visual qualities (engaging, instinctive, ambient, and derivative) underlying nature-induced relaxation, and show that nature relatedness influences the degree to which nature video clips elicit relaxation. We discuss design implications for creating personalized digital nature. 
    more » « less
  4. Concerns about the risks and harms posed by artificial intelligence (AI) have resulted in significant study into algorithmic transparency, giving rise to a sub-field known as Explainable AI (XAI). Unfortunately, despite a decade of development in XAI, an existential challenge remains: progress in research has not been fully translated into the actual implementation of algorithmic transparency by organizations. In this work, we test an approach for addressing the challenge by creating transparency advocates, or motivated individuals within organizations who drive a ground-up cultural shift towards improved algorithmic transparency.Over several years, we created an open-source educational workshop on algorithmic transparency and advocacy. We delivered the workshop to professionals across two separate domains to improve their algorithmic transparency literacy and willingness to advocate for change. In the weeks following the workshop, participants applied what they learned, such as speaking up for algorithmic transparency at an organization-wide AI strategy meeting. We also make two broader observations: first, advocacy is not a monolith and can be broken down into different levels. Second, individuals' willingness for advocacy is affected by their professional field. For example, news and media professionals may be more likely to advocate for algorithmic transparency than those working at technology start-ups. 
    more » « less
  5. Abstract The emergence and dissemination of new legal ideas can play an important role in sparking change in the way activists in marginalized communities understand their rights and pursue their objectives. How and why do the legal beliefs of such communities evolve? We argue that the vigorous advocacy of new legal ideas by entrepreneurs and the harnessing of specialized media to help disseminate those ideas are important mechanisms in this evolution. We use the rise of marriage equality as a central legal priority in the mainstream American LGBTQ+ rights movement as a case study to illustrate this phenomenon. Using a mixed-methods analysis of Evan Wolfson’s legal advocacy and an examination ofThe Advocate, we investigate how Wolfson developed and disseminated legal ideas about same-sex marriage. We show how this advocacy eventually dominated discussion of the issue among elite LGBTQ+ legal actors and the nation’s largest LGBTQ+ publication. However, Wolfson’s advocacy tended to emphasize LGBTQ+ integration into “mainstream” American culture and prioritized the interests and values of relatively privileged subgroups within the LGBTQ+ community. Our research informs our understanding of the interplay between legal advocacy and media reporting in the development of LGBTQ+ rights claims and the strategies adopted to achieve them. 
    more » « less