Recommending Themes for Ad Creative Design via Visual-Linguistic Representations

Abstract

There is a perennial need in the online advertising industry to refresh ad creatives, i.e., images and text used for enticing online users towards a brand. Such refreshes are required to reduce the likelihood of ad fatigue among online users, and to incorporate insights from other successful campaigns in related product categories. Given a brand, to come up with themes for a new ad is a painstaking and time consuming process for creative strategists. Strategists typically draw inspiration from the images and text used for past ad campaigns, as well as world knowledge on the brands. To automatically infer ad themes via such multimodal sources of information in past ad campaigns, we propose a theme (keyphrase) recommender system for ad creative strategists. The theme recommender is based on aggregating results from a visual question answering (VQA) task, which ingests the following: (i) ad images, (ii) text associated with the ads as well as Wikipedia pages on the brands in the ads, and (iii) questions around the ad. We leverage transformer based cross-modality encoders to train visual-linguistic representations for our VQA task. We study two formulations for the VQA task along the lines of classification and ranking; via experiments on a public dataset, we show that cross-modal representations lead to significantly better classification accuracy and ranking precision-recall metrics. Cross-modal representations show better performance compared to separate image and text representations. In addition, the use of multimodal information shows a significant lift over using only textual or visual information.

TSI: an Ad Text Strength Indicator using Text-to-CTR and Semantic-Ad-Similarity

“…Understanding ad images and text for the purposes of ad creative optimization is an area of active research. While A/B tests with a large pool of creatives to efficiently learn which creative works best (popularly known as dynamic creative optimization in the industry) [11,24] are a common practice in the industry, recent works [8,16,17,26] have focused on models to understand ad creatives for gathering insights and automating the ad creation process. Understanding content in ad images was studied in [8,23], where manual annotations were gathered from crowdsourced workers for: ad category, reasons to buy products advertised in the ad, and expected user responses given the ad.…”

“…Understanding content in ad images was studied in [8,23], where manual annotations were gathered from crowdsourced workers for: ad category, reasons to buy products advertised in the ad, and expected user responses given the ad. Leveraging the dataset in [8], [16,26] studied recommending keyphrases for guiding a brand's creative design using the Wikipedia pages of associated brands. In [15], semantically similar ads were leveraged to automate ad image search given ad text.…”

VisualTextRank: Unsupervised Graph-based Content Extraction for Automating Ad Text to Image Search

“…In [8], ad image content was studied using computer vision models, and their dataset had manual annotations for: ad category, reasons to buy products advertised in the ad, and expected user response given the ad. Using this dataset, [16,24] used ranking models to recommend themes for ad creative design using a brand's Wikipedia page. In [17], object tag recommendations for improving an ad image was studied using data from A/B tests.…”

Interpretable Contextual Team-aware Item Recommendation: Application in Multiplayer Online Battle Arena Games

“…Recently, the Transformer [25] has been a foundation for many competitive methods. This architecture has been shown to efficiently encode various types of information useful for recommendation systems [26]. A personalized re-ranking model is proposed in [19], which captures in its encoding layer the interactions between users and items to produce an interpretable re-ranked recommendation list.…”