arXiv subjects

Siva Viswanathan

Publications and source records attributed to Siva Viswanathan.

4 recordsLinked to original sources

arXiv2026

DIRECT: Decomposing Audience Preference and Creative Effect in Visual Content Analytics

Which visual choices make a post perform better? A growing literature answers this question with pooled coefficients estimated across many creators, which platforms translate into creative recommendations. We show that these coefficients blend two distinct patterns that can point in opposite directions for the same attribute. The first, audience preference, arises because creators who favor a style attract differently composed audiences, so their posts perform differently because of who is watching, not what any single post does. The second, creative effect, captures how a creator's audience responds when she departs from her usual look. Pooled estimation averages the two, and audience preference can be large enough to reverse the signal that creative direction requires. We propose DIRECT (Decomposed Identification of Response Effects via Causal Tools), a panel-based causal-inference framework that separates them, combining the Mundlak between-within decomposition with double machine learning over latent vision-language treatments that co-vary within a creator. We apply it to 232,088 sponsored Instagram beauty posts across 1,527 creators and 11 CLIP-derived visual style axes. The two carry opposite signs on 4 of 11 attributes, and on 2 of 11 the pooled coefficient itself recommends the wrong creative direction: on skin tone, it favors lighter representations while the creative effect points the other way, since a creator's audience engages more with tones darker than her baseline. On held-out creators, prescribing from the pooled coefficient forgoes 31% of the achievable engagement gain. We contribute a diagnosis of estimand mismatch in visual content analytics, a framework that recovers the decision-relevant estimand from observational panel data, and three portable diagnostics for auditing whether pooled estimates support the decisions they inform.

econ.EM↗

arXiv2026

Estimating Visual Attribute Effects in Advertising from Observational Data: A Deepfake-Informed Double Machine Learning Approach

Digital advertising increasingly relies on visual content, yet marketers lack rigorous methods for understanding how specific visual attributes causally affect consumer engagement. This paper addresses a fundamental methodological challenge: estimating causal effects when the treatment, such as a model's skin tone, is an attribute embedded within the image itself. Standard approaches like Double Machine Learning (DML) fail in this setting because vision encoders entangle treatment information with confounding variables, producing severely biased estimates. We develop DICE-DML (Deepfake-Informed Control Encoder for Double Machine Learning), a framework that leverages generative AI to disentangle treatment from confounders. The approach combines three mechanisms: (1) deepfake-generated image pairs that isolate treatment variation; (2) DICE-Diff adversarial learning on paired difference vectors, where background signals cancel to reveal pure treatment fingerprints; and (3) orthogonal projection that geometrically removes treatment-axis components. In simulations with known ground truth, DICE-DML reduces root mean squared error by 73-97% compared to standard DML, with the strongest improvement (97.5%) at the null effect point, demonstrating robust Type I error control. Applying DICE-DML to 232,089 Instagram influencer posts, we estimate the causal effect of skin tone on engagement. Standard DML produces diagnostically invalid results (negative outcome R^2), while DICE-DML achieves valid confounding control (R^2 = 0.63) and estimates a marginally significant negative effect of darker skin tone (-522 likes; p = 0.062), substantially smaller than the biased standard estimate. Our framework provides a principled approach for causal inference with visual data when treatments and confounders coexist within images.

cs.AI↗

arXiv2025

What Exactly is a Deepfake?

Deepfake technologies are often associated with deception, misinformation, and identity fraud, raising legitimate societal concerns. Yet such narratives may obscure a key insight: deepfakes embody sophisticated capabilities for sensory manipulation that can alter human perception, potentially enabling beneficial applications in domains such as healthcare and education. Realizing this potential, however, requires understanding how the technology is conceptualized across disciplines. This paper analyzes 826 peer-reviewed publications from 2017 to 2025 to examine how deepfakes are defined and understood in the literature. Using large language models for content analysis, we categorize deepfake conceptualizations along three dimensions: Identity Source (the relationship between original and generated content), Intent (deceptive versus non-deceptive purposes), and Manipulation Granularity (holistic versus targeted modifications). Results reveal substantial heterogeneity that challenges simplified public narratives. Notably, a subset of studies discuss non-deceptive applications, highlighting an underexplored potential for social good. Temporal analysis shows an evolution from predominantly threat-focused views (2017 to 2019) toward recognition of beneficial applications (2022 to 2025). This study provides an empirical foundation for developing nuanced governance and research frameworks that distinguish applications warranting prohibition from those deserving support, showing that, with safeguards, deepfakes' realism can serve important social purposes beyond deception.

cs.CY↗

arXiv2025

From Deception to Perception: The Surprising Benefits of Deepfakes for Detecting, Measuring, and Mitigating Bias

While deepfake technologies have predominantly been criticized for potential misuse, our study demonstrates their significant potential as tools for detecting, measuring, and mitigating biases in key societal domains. By employing deepfake technology to generate controlled facial images, we extend the scope of traditional correspondence studies beyond mere textual manipulations. This enhancement is crucial in scenarios such as pain assessments, where subjective biases triggered by sensitive features in facial images can profoundly affect outcomes. Our results reveal that deepfakes not only maintain the effectiveness of correspondence studies but also introduce groundbreaking advancements in bias measurement and correction techniques. This study emphasizes the constructive role of deepfake technologies as essential tools for advancing societal equity and fairness.

cs.CV↗