Hasil untuk "Advertising"

H. Bauer, S. Barnes, T. Reichardt et al.

Yizhi Liu, Balaji Padmanabhan, Siva Viswanathan

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.

Ahmad Alemari, Pritam Sen, Cristian Borcea

Since most countries are coming up with online privacy regulations, such as GDPR in the EU, online publishers need to find a balance between revenue from targeted advertisement and user privacy. One way to be able to still show targeted ads, based on user personal and behavioral information, is to employ Federated Learning (FL), which performs distributed learning across users without sharing user raw data with other stakeholders in the publishing ecosystem. This paper presents AdFL, an FL framework that works in the browsers to learn user ad preferences. These preferences are aggregated in a global FL model, which is then used in the browsers to show more relevant ads to users. AdFL can work with any model that uses features available in the browser such as ad viewability, ad click-through, user dwell time on pages, and page content. The AdFL server runs at the publisher and coordinates the learning process for the users who browse pages on the publisher's website. The AdFL prototype does not require the client to install any software, as it is built utilizing standard APIs available on most modern browsers. We built a proof-of-concept model for ad viewability prediction that runs on top of AdFL. We tested AdFL and the model with two non-overlapping datasets from a website with 40K visitors per day. The experiments demonstrate AdFL's feasibility to capture the training information in the browser in a few milliseconds, show that the ad viewability prediction achieves up to 92.59% AUC, and indicate that utilizing differential privacy (DP) to safeguard local model parameters yields adequate performance, with only modest declines in comparison to the non-DP variant.

Tongtong Liu, Zhaohui Wang, Meiyue Qin et al.

The integration of Large Language Models (LLMs) with retrieval systems has shown promising potential in retrieving documents (docs) or advertisements (ads) for a given query. Existing LLM-based retrieval methods generate numeric or content-based DocIDs to retrieve docs/ads. However, the one-to-few mapping between numeric IDs and docs, along with the time-consuming content extraction, leads to semantic inefficiency and limits scalability in large-scale corpora. In this paper, we propose the Real-time Ad REtrieval (RARE) framework, which leverages LLM-generated text called Commercial Intentions (CIs) as an intermediate semantic representation to directly retrieve ads for queries in real-time. These CIs are generated by a customized LLM injected with commercial knowledge, enhancing its domain relevance. Each CI corresponds to multiple ads, yielding a lightweight and scalable set of CIs. RARE has been implemented in a real-world online system, handling daily search volumes in the hundreds of millions. The online implementation has yielded significant benefits: a 5.04% increase in consumption, a 6.37% rise in Gross Merchandise Volume (GMV), a 1.28% enhancement in click-through rate (CTR) and a 5.29% increase in shallow conversions. Extensive offline experiments show RARE's superiority over ten competitive baselines in four major categories.

Zhaoyi Joey Hou, Adriana Kovashka, Xiang Lorraine Li

Evaluating creativity is challenging, even for humans, not only because of its subjectivity but also because it involves complex cognitive processes. Inspired by work in marketing, we attempt to break down visual advertisement creativity into atypicality and originality. With fine-grained human annotations on these dimensions, we propose a suite of tasks specifically for such a subjective problem. We also evaluate the alignment between state-of-the-art (SoTA) vision language models (VLMs) and humans on our proposed benchmark, demonstrating both the promises and challenges of using VLMs for automatic creativity assessment.

Muhammad Imran Zaman, Nisar Ahmed

This paper presents a novel deep learning-based approach for simultaneous age and gender classification from facial images, designed to enhance the effectiveness of targeted advertising campaigns. We propose a custom Convolutional Neural Network (CNN) architecture, optimized for both tasks, which leverages the inherent correlation between age and gender information present in facial features. Unlike existing methods that often treat these tasks independently, our model learns shared representations, leading to improved performance. The network is trained on a large, diverse dataset of facial images, carefully pre-processed to ensure robustness against variations in lighting, pose, and image quality. Our experimental results demonstrate a significant improvement in gender classification accuracy, achieving 95%, and a competitive mean absolute error of 5.77 years for age estimation. Critically, we analyze the performance across different age groups, identifying specific challenges in accurately estimating the age of younger individuals. This analysis reveals the need for targeted data augmentation and model refinement to address these biases. Furthermore, we explore the impact of different CNN architectures and hyperparameter settings on the overall performance, providing valuable insights for future research.

Xinwei Long, Kai Tian, Peng Xu et al.

Large language models (LLMs) have taken a great step towards AGI. Meanwhile, an increasing number of domain-specific problems such as math and programming boost these general-purpose models to continuously evolve via learning deeper expertise. Now is thus the time further to extend the diversity of specialized applications for knowledgeable LLMs, though collecting high quality data with unexpected and informative tasks is challenging. In this paper, we propose to use advertisement (ad) videos as a challenging test-bed to probe the ability of LLMs in perceiving beyond the objective physical content of common visual domain. Our motivation is to take full advantage of the clue-rich and information-dense ad videos' traits, e.g., marketing logic, persuasive strategies, and audience engagement. Our contribution is three-fold: (1) To our knowledge, this is the first attempt to use ad videos with well-designed tasks to evaluate LLMs. We contribute AdsQA, a challenging ad Video QA benchmark derived from 1,544 ad videos with 10,962 clips, totaling 22.7 hours, providing 5 challenging tasks. (2) We propose ReAd-R, a Deepseek-R1 styled RL model that reflects on questions, and generates answers via reward-driven optimization. (3) We benchmark 14 top-tier LLMs on AdsQA, and our \texttt{ReAd-R}~achieves the state-of-the-art outperforming strong competitors equipped with long-chain reasoning capabilities by a clear margin.

Abdillah Ahsan, Nadira Amalia, Krisna Puji Rahmayanti et al.

Objective Efforts to implement health tax policies to control the consumption of harmful commodities and enhance public health outcomes have garnered substantial recognition globally. However, their successful adoption remains a complex endeavour. This investigates the challenges and opportunities surrounding health tax implementation, with a particular focus on subnational government in Indonesia, where the decentralisation context of health tax remains understudied.Design Employing a qualitative methodology using a problem-driven political economy analysis approach.Setting We are collecting data from a total of 12 focus group discussions (FGDs) conducted between July and September 2022 in three provinces—Lampung, Special Region of/Daerah Istimewa Yogyakarta and Bali, each chosen to represent a specific commodity: tobacco, sugar-sweetened beverages (SSBs) and alcoholic beverages—we explore the multifaceted dynamics of health tax policies.Participant These FGDs involved a mean of 10 participants in each FGD, representing governmental institutions, non-governmental organisations and consumers.Results Our findings reveal that health tax policies have the potential to contribute significantly to public health. Consumers understand tobacco’s health risks, and cultural factors influence both tobacco and alcohol consumption. For SSBs, the consumers lack awareness of long-term health risks is concerning. Finally, bureaucratic complexiting and decentralised government hinder implementation for all three commodities.Conclusion Furthermore, this study underscores the importance of effective policy communication. It highlights the importance of earmarking health tax revenues for public health initiatives. It also reinforces the need to see health taxes as one intervention as part of a comprehensive public health approach including complementary non-fiscal measures like advertising restrictions and standardised packaging. Addressing these challenges is critical for realising the full potential of health tax policies.

Vageesh Saxena, Benjamin Bashpole, Gijs Van Dijck et al.

Human trafficking (HT) remains a critical issue, with traffickers increasingly leveraging online escort advertisements (ads) to advertise victims anonymously. Existing detection methods, including Authorship Attribution (AA), often center on text-based analyses and neglect the multimodal nature of online escort ads, which typically pair text with images. To address this gap, we introduce MATCHED, a multimodal dataset of 27,619 unique text descriptions and 55,115 unique images collected from the Backpage escort platform across seven U.S. cities in four geographical regions. Our study extensively benchmarks text-only, vision-only, and multimodal baselines for vendor identification and verification tasks, employing multitask (joint) training objectives that achieve superior classification and retrieval performance on in-distribution and out-of-distribution (OOD) datasets. Integrating multimodal features further enhances this performance, capturing complementary patterns across text and images. While text remains the dominant modality, visual data adds stylistic cues that enrich model performance. Moreover, text-image alignment strategies like CLIP and BLIP2 struggle due to low semantic overlap and vague connections between the modalities of escort ads, with end-to-end multimodal training proving more robust. Our findings emphasize the potential of multimodal AA (MAA) to combat HT, providing LEAs with robust tools to link ads and disrupt trafficking networks.

Dildar Ali, Suman Banerjee, Yamuna Prasad

The selection of influential billboard slots remains an important problem in billboard advertisements. Existing studies on this problem have not considered the case of context-specific influence probability. To bridge this gap, in this paper, we introduce the Context Dependent Influential Billboard Slot Selection Problem. First, we show that the problem is NP-hard. We also show that the influence function holds the bi-monotonicity, bi-submodularity, and non-negativity properties. We propose an orthant-wise Stochastic Greedy approach to solve this problem. We show that this method leads to a constant-factor approximation guarantee. Subsequently, we propose an orthant-wise Incremental and Lazy Greedy approach. In a generic sense, this is a method for maximizing a bi-submodular function under the cardinality constraint, which may also be of independent interest. We analyze the performance guarantee of this algorithm as well as time and space complexity. The proposed solution approaches have been implemented with real-world billboard and trajectory datasets. We compare the performance of our method with several baseline methods, and the results are reported. Our proposed orthant-wise stochastic greedy approach leads to significant results when the parameters are set properly with reasonable computational overhead.

Ashirbad Mishra, Soumik Dey, Marshall Wu et al.

Online sellers and advertisers are recommended keyphrases for their listed products, which they bid on to enhance their sales. One popular paradigm that generates such recommendations is Extreme Multi-Label Classification (XMC), which involves tagging/mapping keyphrases to items. We outline the limitations of using traditional item-query based tagging or mapping techniques for keyphrase recommendations on E-Commerce platforms. We introduce GraphEx, an innovative graph-based approach that recommends keyphrases to sellers using extraction of token permutations from item titles. Additionally, we demonstrate that relying on traditional metrics such as precision/recall can be misleading in practical applications, thereby necessitating a combination of metrics to evaluate performance in real-world scenarios. These metrics are designed to assess the relevance of keyphrases to items and the potential for buyer outreach. GraphEx outperforms production models at eBay, achieving the objectives mentioned above. It supports near real-time inferencing in resource-constrained production environments and scales effectively for billions of items.

Juliana Barbosa, Sunandan Chakraborty, Juliana Freire

Wildlife traffickers are increasingly carrying out their activities in cyberspace. As they advertise and sell wildlife products in online marketplaces, they leave digital traces of their activity. This creates a new opportunity: by analyzing these traces, we can obtain insights into how trafficking networks work as well as how they can be disrupted. However, collecting such information is difficult. Online marketplaces sell a very large number of products and identifying ads that actually involve wildlife is a complex task that is hard to automate. Furthermore, given that the volume of data is staggering, we need scalable mechanisms to acquire, filter, and store the ads, as well as to make them available for analysis. In this paper, we present a new approach to collect wildlife trafficking data at scale. We propose a data collection pipeline that combines scoped crawlers for data discovery and acquisition with foundational models and machine learning classifiers to identify relevant ads. We describe a dataset we created using this pipeline which is, to the best of our knowledge, the largest of its kind: it contains almost a million ads obtained from 41 marketplaces, covering 235 species and 20 languages. The source code is publicly available at \url{https://github.com/VIDA-NYU/wildlife_pipeline}.

Irfan alimirzaei, Seyyed Mahmoud hoseini

The current research aimed to identify the functional areas with relative advantage to help empower and develop private agricultural extension consultants and related economic enterprises at the level of two provinces of Tehran and Alborz. Based on this, considering the possibility of applying the findings in the field of practice, this research is among the decision-oriented applied research in terms of general orientation and goal. From the point of view of the researcher's degree of control over the variables under study and the background conditions of the research, it is considered a type of non-experimental research that describes the phenomena under investigation in a single period of time. The statistical population of the research included 25 key experts from the public and sectors, whom were purposefully selected and examined. The research method was based on documentary studies, semi-structured interviews, and quantitative survey using a researcher-made questionnaire. In order to identify functional gaps in the field of performance of private promotion companies, or in other words, to identify the degree of relative advantage of the various service delivery areas of the mentioned companies in the region, the weighted average score of the differences using the needs assessment relationship was calculated. Based on the findings from the analysis of the opinions of knowledgeable sample people and the calculated relative advantages, "advertising, stimulating, organizing and strengthening the demand dimension for research and development processes and agricultural innovations" is the most prioritized; and "Implementation of monitoring and evaluation plans to ensure the quality of promotion and evaluation services from active businesses in the region" were identified as the least priority service areas for focusing on the role of private agricultural consultants in the region.

Jacek Lorkowski, Mieczyslaw Pokorski

Footwear fashion is an instance of a socially formed attitude affecting somatic population health. High-heeled, particularly pointy-toed shoes are posed to structurally distort and overload feet leading to musculoskeletal sequelae. Here we compiled multilanguage website images presenting female footwear produced by the top manufacturers to assess the advertising effects on the prevailing height of heels worn by women. The method was based on the analysis of websites using the command “woman shoes” in scores of languages of the Internet Google browser. We then compared the results of the internet search with those of a live street surveillance of the footwear worn by 100 adult women in the downtown Warsaw metropolis in Poland. We found that stiletto heels with pointed shoe tips significantly predominated in images representing the countries belonging to the Western cultural sphere compared to less affluent world areas where low or flat heels prevailed. However, we noted a gradual departure from the fashion of high heels over the last decade, confirmed by live street surveillance, liable to reflect changes in the website presentations of top shoe manufacturers consistent with increasing awareness of potential harm by high heels. Yet the female aptitude for wearing more physiologic shoe models appears to exceed that resulting from marketing campaigns. Doing away with high-heeled pointy-toed shoes requires intensification of pro-health preventive measures in the field of public health.

Marcel Kurt Mainka, Oksana Melnichenko , Artem Tsybrovskyi et al.

The main goal of the research is to study and evaluate modern socially responsible marketing strategies of global sports brands for the development of proposals for the domestic sports business. The article examines the role and significance of the social responsibility of business in modern marketing strategies of companies. The essence of socially responsible marketing and types of marketing strategies have been studied. The key marketing strategies that are relevant under modern market conditions are distinguished. It was determined that charity, sponsorship, and active participation in environmental protection programs are the most popular forms of social responsibility of sports companies. The largest and most popular sports companies were chosen on the basis of the rating evaluation results of the world's sports brands. According to the official websites of the world's leading sports companies, the content of strategic marketing initiatives that take place in their management practice was analyzed. It was found that all global sports brands have a high level of activity in the field of social responsibility of business. Among the most popular marketing strategies, these companies use the production of goods from ecological raw materials, the strategy of transformational cyclicality and energy efficiency, the promotion of a healthy lifestyle among potential and contact audiences, the involvement of consumers in programs for the preservation and restoration of natural resources, the observance of human rights, the strategy of inclusiveness and equality for all categories of consumers. Studies of the Ukrainian market of sports brands have shown that many new companies have appeared in the country in recent years, however, their level of social business responsibility remains low compared to global sports brands. In order to create favourable conditions for the success of Ukrainian sports companies on the basis of the best global practice, strategic areas of socially responsible marketing were proposed. The main elements of marketing strategies were identified as key elements of the implementation of these strategic initiatives, including reputational capital and branding, active promotion technologies based on digital potential, socially significant long-term values, unity of business interests and the interests of society.

Raquel Quevedo-Redondo, Marta Rebolledo, Nuria Navarro-Sierra

The changes brought by new technologies and the ensuing rapid development of the communication field have resulted in an increasing number of studies on politicians’ use of the internet and social media. However, while election campaigns have been the predominant research area in political communication scholarship, music has not yet been taken as an object of study alongside spectacularisation and politainment. Aside from some preliminary studies, systematic research on music in politics is scarce. The literature holds that music is a universal language. Music in politics can therefore be deemed to be an identification tool that can help politicians connect with voters and bring together positions between the different actors of international relations. This is an exploratory study about the use of music in political campaigning. It is focused on the role played by the Spotify playlists created by the main political parties in recent election campaigns in Spain. The initial hypothesis is that some of the candidates strategically selected songs to be shared with their followers. A quantitative content analysis (N = 400) of some Spotify playlists showed that there were significant differences in the selection of songs among the different political parties. This research contributes to the understanding of how Spotify has been used for electoral campaigning, as well as shedding some light on the current communication literature on music and politics.

Dang Minh Nguyen, Chenfei Wang, Yan Shen et al.

Graph Neural Network (GNN) is the trending solution for item retrieval in recommendation problems. Most recent reports, however, focus heavily on new model architectures. This may bring some gaps when applying GNN in the industrial setup, where, besides the model, constructing the graph and handling data sparsity also play critical roles in the overall success of the project. In this work, we report how GNN is applied for large-scale e-commerce item retrieval at Shopee. We introduce our simple yet novel and impactful techniques in graph construction, modeling, and handling data skewness. Specifically, we construct high-quality item graphs by combining strong-signal user behaviors with high-precision collaborative filtering (CF) algorithm. We then develop a new GNN architecture named LightSAGE to produce high-quality items' embeddings for vector search. Finally, we design multiple strategies to handle cold-start and long-tail items, which are critical in an advertisement (ads) system. Our models bring improvement in offline evaluations, online A/B tests, and are deployed to the main traffic of Shopee's Recommendation Advertisement system.

Martin Bichler, Alok Gupta, Matthias Oberlechner

The transition of display ad exchanges from second-price auctions (SPA) to first-price auctions (FPA) has raised questions about its impact on revenue. Auction theory predicts the revenue equivalence between these two auction formats. However, display ad auctions are different from standard models in auction theory. First, automated bidding agents cannot easily derive equilibrium strategies in FPA because information regarding competitors is not readily available. Second, due to principal-agent problems, bidding agents typically maximize return-on-investment (ROI), not payoff. The literature on learning agents for real-time bidding is growing because of the practical relevance of this area; most research has found that learning agents do not converge to an equilibrium. Specifically, research on algorithmic collusion in display ad auctions has argued that FPA can induce symmetric Q-learning agents to tacitly collude, resulting in bids below equilibrium, leading to lower revenue compared to the SPA. Whether bids are in equilibrium cannot easily be determined from field data since the underlying values of bidders are unknown. In this paper, we draw on analytical modeling and numerical experiments and explore the convergence behavior of widespread online learning algorithms in both complete and incomplete information models. Contrary to prior results, we show that there are no systematic deviations from equilibrium behavior. We also explore the differences in revenue of the FPA and SPA, which have not been done for utility functions relevant to this domain, such as ROI. We show that learning algorithms also converge to equilibrium. Still, revenue equivalence does not hold, indicating that collusion may not be the explanation for lower revenue with FPA, and the change in auction format might have had substantial and non-obvious consequences for ad exchanges and advertisers.

Stephanie A. S. Staras, Carma L. Bylund, Michaela D. Mullis et al.

Abstract Background In the United States, human papillomavirus (HPV) vaccination rates remain low. The President’s Cancer Panel suggests that effective messaging about the HPV vaccination focus on the vaccine’s safety, efficacy, ability to prevent cancer, and recommendation at ages 11- to 12-years. We aimed to develop messages about HPV vaccine that include the President Cancer Panel’s suggestions and were acceptable to caregivers of adolescents. Methods From August to October 2020, we conducted one-hour, Zoom videoconference focus groups with caregivers who lived in Florida, had an 11- to 12-year-old child, and had not had any of their children receive the HPV vaccine. Focus group moderators asked caregivers to react to three videos of clinician (i.e., MD, DO, APRN, PA) recommendations and three text message reminders. Thematic analysis was conducted using the constant comparative method and led by one author with qualitative analysis expertise. Two additional authors validated findings. Results Caregivers (n = 25 in six groups) were primarily non-Hispanic white (84%) and educated (64% had at least an Associate’s degree). Approximately a third of caregivers had delayed (44%) or decided against a vaccine for their child (36%). Caregivers described six preferred message approaches: recognize caregivers’ autonomy, balanced benefits and risks, trustworthy sources, increased feasibility of appointment scheduling, information prior to decision point, and preferred personalized information. Caregivers expressed a desire to have the follow-up doses mentioned in the introduction. Conclusions HPV vaccine messages, whether delivered by a clinician or via text message, will be more acceptable to caregivers if they approach HPV vaccination as the caregivers’ decision, and include information from trusted sources to help caregivers make an informed choice.

Atanu R. Sinha, Gautam Choudhary, Mansi Agarwal et al.

When a business sells to another business (B2B), the buying business is represented by a group of individuals, termed account, who collectively decide whether to buy. The seller advertises to each individual and interacts with them, mostly by digital means. The sales cycle is long, most often over a few months. There is heterogeneity among individuals belonging to an account in seeking information and hence the seller needs to score the interest of each individual over a long horizon to decide which individuals must be reached and when. Moreover, the buy decision rests with the account and must be scored to project the likelihood of purchase, a decision that is subject to change all the way up to the actual decision, emblematic of group decision making. We score decision of the account and its individuals in a dynamic manner. Dynamic scoring allows opportunity to influence different individual members at different time points over the long horizon. The dataset contains behavior logs of each individual's communication activities with the seller; but, there are no data on consultations among individuals which result in the decision. Using neural network architecture, we propose several ways to aggregate information from individual members' activities, to predict the group's collective decision. Multiple evaluations find strong model performance.