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

• URL: http://arxiv.org/abs/2608.26584v1
• Date: Thu, 27 Aug 2026 03:50:01 GMT
• Title: DIRECT: Decomposing Audience Preference and Creative Effect in Visual Content Analytics
• Abstract summary: We show that pooled coefficients blend two distinct patterns that can point in opposite directions for the same attribute.<n>We propose a panel-based causal-inference framework that separates them.<n>We apply it to 232,088 sponsored Instagram beauty posts across 1,527 creators and 11 CLIP-derived visual style axes.
• Score: 3.964305334218188
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning [73.40085256022111]
  We propose Perceive-to-Reason (P2R), a unified framework that formulates fine-grained visual reasoning as a two-stage process.<n>P2R localizes question-relevant evidence as a Perceiver, and then answers the question as a Reasoner based on the annotated image and cropped regions.<n>PRA-GRPO is a role-aware reinforcement learning strategy that alternates between perception-focused and reasoning-focused updates.
  arXiv  Detail & Related papers  (2026-07-01T17:24:26Z)
• Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective [83.75710105509076]
  This paper aims to shed light on the role of design choices on learning and generalization dynamics.<n>The underlying challenge is that design choices are entangled together, making their contribution to learning and generalization difficult to attribute.<n> Experiments on three base models and two datasets reveal new understanding on the role of various design choices on learning and generalization dynamics.
  arXiv  Detail & Related papers  (2026-01-30T04:09:06Z)
• Free Energy-Based Modeling of Emotional Dynamics in Video Advertisements [0.0]
  We have quantified "pleasantness," "surprise," and "habituation" solely from scene-level expression features of advertising videos.<n>This work can be extended by integrating a wider range of expression elements and validating the approach through subjective ratings.
  arXiv  Detail & Related papers  (2025-12-22T06:51:41Z)
• Simple Lines, Big Ideas: Towards Interpretable Assessment of Human Creativity from Drawings [18.09092203643732]
  We propose a data-driven framework for automatic and interpretable creativity assessment from drawings.<n>Motivated by the cognitive evidence proposed in [6] that creativity can emerge from both what is drawn (content) and how it is drawn (style), we reinterpret the creativity score as a function of these two complementary dimensions.
  arXiv  Detail & Related papers  (2025-11-17T02:16:01Z)
• BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception [67.89135437537179]
  We introduce BLINK-Twice, a vision-centric reasoning benchmark grounded in challenging perceptual tasks.<n>Instead of relying on external knowledge, our tasks require models to reason from visual content alone.<n>Compared to prior perception benchmarks, it moves beyond shallow perception and requires fine-grained observation and analytical reasoning.
  arXiv  Detail & Related papers  (2025-10-10T13:14:13Z)
• Mitigating Multimodal Hallucinations via Gradient-based Self-Reflection [49.26064449816502]
  We propose a Gradient-based Influence-Aware Constrained Decoding (GACD) method to address text-visual bias and co-occurrence bias.<n>GACD effectively reduces hallucinations and improves the visual grounding of MLLM outputs.
  arXiv  Detail & Related papers  (2025-09-03T08:13:52Z)
• Exploring the Individuality and Collectivity of Intents behind Interactions for Graph Collaborative Filtering [9.740376003100437]
  We propose a novel recommendation framework designated as Bilateral Intent-guided Graph Collaborative Filtering (BIGCF) Specifically, we take a closer look at user-item interactions from a causal perspective and put forth the concepts of individual intent. To counter the sparsity of implicit feedback, the feature distributions of users and items are encoded via a Gaussian-based graph generation strategy.
  arXiv  Detail & Related papers  (2024-05-15T02:31:26Z)
• Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations [67.92679668612858]
  We propose the Consensus Network (Css-Net), inspired by the psychological concept that groups outperform individuals. Css-Net comprises two core components: (1) a consensus module with four diverse compositors, each generating distinct image-text embeddings; and (2) a Kullback-Leibler divergence loss that encourages learning of inter-compositor interactions. On benchmark datasets, particularly FashionIQ, Css-Net demonstrates marked improvements. Notably, it achieves significant recall gains, with a 2.77% increase in R@10 and 6.67% boost in R@50, underscoring its
  arXiv  Detail & Related papers  (2023-06-03T11:50:44Z)
• Modeling Content Creator Incentives on Algorithm-Curated Platforms [76.53541575455978]
  We study how algorithmic choices affect the existence and character of (Nash) equilibria in exposure games. We propose tools for numerically finding equilibria in exposure games, and illustrate results of an audit on the MovieLens and LastFM datasets.
  arXiv  Detail & Related papers  (2022-06-27T08:16:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.