Relevant Ads Research Articles

OPTIMIZING PROGRAMMATIC ADVERTISING: A MACHINE LEARNING APPROACH TO PREDICTIVE AD TARGETING

In the ever-evolving landscape of digital advertising, programmatic advertising has emerged as a pivotal tool for automating ad placement and targeting audiences at scale. However, traditional methods often fall short in accurately predicting user behavior and delivering relevant ads to the right audiences. This study explores the potential of machine learning (ML) techniques to enhance predictive ad targeting within the programmatic advertising ecosystem. By applying a range of supervised and unsupervised ML models, including decision trees, neural networks, and clustering algorithms, we assess the ability of these models to improve ad relevance and engagement while optimizing budget allocation. Our findings reveal that ML-driven predictive targeting significantly increases click-through rates (CTR) and conversion rates compared to conventional targeting strategies. This research highlights the implications of using ML to improve ad targeting precision, reduce ad spend wastage, and enhance user experience. These insights contribute to the advancement of programmatic advertising strategies by demonstrating the transformative impact of AI and ML on audience segmentation and predictive ad delivery.

TRANSCENDING BOUNDARIES – REPRESENTATION OF CHANGING GENDER DYNAMICS IN SELECT INDIAN TELEVISION ADVERTISEMENTS

Advertisements are primarily intended to persuade the consumers to buy a particular brand of product. In modern times Television advertisements or TV commercials as they are known, have emerged as one of the most visible and popular form of advertisements. Traditionally, selling a product entailed roping in a celebrity to either pose with the product or to highlight its advantages over other products. But the advent of various domestic and foreign channels offered the viewers the option to skip the advertisements and switch over to more interesting content in other channels. Besides, the stiff competition between the brands necessitated the advertisements to be more creative, resulting in the incorporation of engaging storylines. Thus, advertisements have transitioned from a means for merely selling products to cultural artefacts mirroring the socio-cultural practices and values of the society. They portray social norms, cultural reality, and gender patterns in keeping with the patriarchal ideology. Culture profoundly impacts gender-related behavior, roles, values, identity, and their perception in various social contexts. It governs the expectations placed on men and women and influences their attitudes and behavior. Since advertisements are predominantly created by men with the intention of appeasing the male consumers, women are often objectified. The recent decades have seen women progress in leaps and bounds but the advertisements have been slow in acknowledging their achievements. The winds of change have been very subtle but steady progress is being made in making progressive and socially relevant ads which has captured man - woman equation from a different angle. This paper proposes to analyze select TV advertisements that appeared after 2000 which show both men and women breaking away from the narrow confines of patriarchy to don new and unconventional roles.

Based on intelligent advertising recommendation and abnormal advertising monitoring system in the field of machine learning

With the rapid development of the Internet, the scale of the online advertising market has expanded rapidly, and display advertising has become the most popular means of publicity. Accurate advertising recommendation is the guarantee of Internet platform revenue, and accurate advertising click rate prediction is the premise of accurate recommendation and abnormal advertising detection. Therefore, such monitoring and recommendation can be achieved through machine learning combined with artificial intelligence, and the application of intelligent AD recommendation systems and abnormal AD monitoring in the field of machine learning represents a complex integration of technologies to improve the precision and effectiveness of digital marketing strategies. Intelligent AD recommendation systems utilize advanced machine learning algorithms to analyze user behavior and preferences to deliver tailored AD content. These systems leverage vast amounts of user data, including browsing history, purchase history, and engagement metrics, to predict and present the most relevant ads. This paper analyzes the data mining in machine learning algorithms and the real-time online recommendation algorithm of Gaussian process, and analyzes the abnormal advertising monitoring system for maintaining the integrity and efficiency of advertising campaigns. By using machine learning technology for pattern recognition and anomaly detection, various measures and indicators of advertising campaigns can be monitored in a vigilant manner.

Divergent Versus Relevant Ads: How Creative Ads Affect Purchase Intention for New Products

Creative ads are applied widely in new product marketing. The present research explores the impact of creative ads (divergent vs. relevant ads) on purchase intention for really new products and incrementally new products. A series of studies concludes that (1) divergent ads are more effective for promoting incrementally new products, (2) relevant ads are more effective for promoting really new products, (3) self-referencing mediates the joint effect of creative ads and product newness on purchase intention, and (4) there is an inverted U-shaped relationship between self-referencing and purchase intention for new products. Theoretically, the authors argue that a moderate amount of self-referencing is particularly desirable—that is, there is a “Goldilocks region” that produces an optimal level of persuasion. They provide guidance to creative ad managers to help them reach the “Goldilocks region” when advertising new products.

A Theory of Irrelevant Advertising: An Agency-Induced Targeting Inefficiency

Ad targeting technology has enabled a highly personalized delivery of online ads. Behind this development is the belief that better targeting will lead to more relevant ads. This paper challenges this lay belief by showing that irrelevant advertising can arise not necessarily from technological imperfection but also from the incentive problem embedded in the ad agency-advertisers relationship. We first demonstrate that the ad agency serving multiple advertisers may strategically allocate an ad impression to a lesser-matched, sometimes totally irrelevant, niche advertiser because future impressions can match better with the mainstream advertiser. We further find that, without a contractual obligation to serve both advertisers, the agency may not deliver completely irrelevant ads to consumers. However, another type of inefficiency can arise where the agency may not send any ad to potentially interested consumers who have a strictly positive match probability with advertisers. These inefficiencies arise due to contractual restrictions, either contractual obligations or budget constraints, when the agency serves multiple advertisers. As such, we endogenize the advertisers’ contractual requirement choices and show how the contractual obligation(s) can arise in equilibrium. Finally, we show that irrelevant ads will not disappear simply because more impressions are available in the market. Our analysis suggests that as the number of impressions increases, the irrelevant ads can persist, but the probability of receiving irrelevant ads decreases. This paper was accepted by Dmitri Kuksov, marketing. Funding: W. Shin gratefully acknowledges financial support from the Brian R. Gamache Endowed Professorship at the University of Florida. Supplemental Material: The online appendix is available at https://doi.org/10.1287/mnsc.2022.4605 .

Categorizing the songbird market through big data and machine learning in the context of Indonesia’s online market

The songbird trade has been identified as a major threat to wild populations, and the bird market has now expanded to online platforms. The study explored the use of machine learning models as a monitoring framework; developed models for taxa identification; applied the best model to understand the current market situation (taxa composition, asking price, and location); and conducted a survey to understand the profile of sellers. The authors found that the machine learning models produced a high level of accuracy in distinguishing relevant ads and identified the songbirds’ taxa. The Support Vector Machine (SVM) was selected as the best model and was used to predict the ad population. The model identified 284,118 songbirds from 247 taxa that were listed online from April 2020 to September 2021. The authors also found that 6.2% of ads listed threatened taxa based on the IUCN Red List. The survey results suggested that songbird sellers are mostly hobbyists or breeders looking for extra income from selling birds. As current studies of the songbird market are mostly conducted offline in the bird markets, transactions by non-bird traders or among hobbyists in the online market are remain underreported. Therefore, monitoring needs to be extended to the online market and to our knowledge, currently there is no applied system or platform is identified for monitoring online songbird market. The result from this study can help fill this gap. Information from the monitoring of the songbird online market in this study may assist stakeholders in formulating corrective action based on the current market situation. • The authors demonstrated the songbird online market monitoring using big data and machine learning. • Machine learning models were compared to identify songbirds in online market. • 284,118 songbirds were identified from 250 taxa within 1.5 years of observation data. • The authors found 6.3% of online advertisements listed IUCN threatened species. • Most sellers are hobbyists and breeders, only 7% of respondents are bird traders.

Generating ad creatives using deep learning for search advertising

We generated advertisement creatives programmatically using deep neural networks. A landing page contains relevant text data, which can be used for generating advertisement creatives, i.e. ads. We treated the ad generation task as a text summarization problem and built a sequence to sequence model. In order to assess the validity of our approach, we conducted experiments on four datasets. Our empirical results showed that our model generated relevant ads on a template-based dataset with moderate hyperparameters. Training the model with more content increased the performance of the model, which we attributed to rigorous hyperparameter tune-up. The choice of word embedding used in the representation of the input altered the model's performance. When the source and the target shared common sequences during training, the model produced the best results.

Native advertising relevance effects and the moderating role of attitudes toward social networking sites

PurposeNative advertising on social media continues to be a popular ad placement for marketers. With native ad-content relevance in need of further exploration regarding individual differences and social media public sentiment waning, this study set out to test the effects of ad-content relevance of native ads varying by users' pre-existing social networking site (SNS) attitude.Design/methodology/approachTwo experiments were conducted with native ads relevant and irrelevant to the surrounding media content with SNS attitude as a measured moderator and perceived ad importance as the mediator.FindingsAcross Instagram and Twitter, SNS attitude moderated the effect of ad relevance on ad responses. Users that had lower SNS attitudes had significantly higher ad ratings that were relevant (vs. irrelevant) to the media content, while those that had higher SNS attitudes did not show differences. The lower SNS attitude individuals showed a greater appreciation for the relevant ads through the mediating effect of perceived importance.Practical implicationsMarketers need to look beyond traditional ad attitude models and craft ad content strategies that consider target audiences' SNS preferences. Layering targeting tactics on Instagram and Twitter such as “interests” and “life events” with demographic targeting could help increase the chances of ad-content relevance. SNSs should advance their ad placement tools and utilize image, speech, and text recognition algorithms to help achieve ad-content relevance for greater ad effectiveness.Originality/valueThis study adds to the literature by identifying SNS attitude as a qualifier of ad-content relevance effect for SNS native ads and uncovering perceived ad importance as the underlying psychological mechanism.

A Machine Learning Approach for Solving the Frozen User Cold-Start Problem in Personalized Mobile Advertising Systems

A domain that has gained popularity in the past few years is personalized advertisement. Researchers and developers collect user contextual attributes (e.g., location, time, history, etc.) and apply state-of-the-art algorithms to present relevant ads. A problem occurs when the user has limited or no data available and, therefore, the algorithms cannot work well. This situation is widely referred in the literature as the ‘cold-start’ case. The aim of this manuscript is to explore this problem and present a prediction approach for personalized mobile advertising systems that addresses the cold-start, and especially the frozen user case, when a user has no data at all. The approach consists of three steps: (a) identify existing datasets and use specific attributes that could be gathered from a frozen user, (b) train and test machine learning models in the existing datasets and predict click-through rate, and (c) the development phase and the usage in a system.

Privacy considerations for online advertising: a stakeholder’s perspective to programmatic advertising

PurposePrivacy considerations have become a topic with increasing interest from academics, industry leaders and regulators. In response to consumers’ privacy concerns, Google announced in 2020 that Chrome would stop supporting third-party cookies in the near future. At the same time, advertising technology companies are developing alternative solutions for online targeting and consumer privacy controls. This paper aims to explore privacy considerations related to online tracking and targeting methods used for programmatic advertising (i.e. third-party cookies, Privacy Sandbox, Unified ID 2.0) for a variety of stakeholders: consumers, AdTech platforms, advertisers and publishers.Design/methodology/approachThis study analyzes the topic of internet user privacy concerns, through a multi-pronged approach: industry conversations to collect information, a comprehensive review of trade publications and extensive empirical analysis. This study uses two methods to collect data on consumer preferences for privacy controls: a survey of a representative sample of US consumers and field data from conversations on web-forums created by tech professionals.FindingsThe results suggest that there are four main segments in the US internet user population. The first segment, consisting of 26% of internet users, is driven by a strong preference for relevant ads and includes consumers who accept the premises of both Privacy Sandbox and Unified ID (UID) 2.0. The second segment (26%) includes consumers who are ambivalent about both sets of premises. The third segment (34%) is driven by a need for relevant ads and a strong desire to prevent advertisers from aggressively collecting data, with consumers who accept the premises of Privacy Sandbox but reject the premises of UID 2.0. The fourth segment (15% of consumers) rejected both sets of premises about privacy control. Text analysis results suggest that the conversation around UID 2.0 is still nascent. Google Sandbox associations seem nominally positive, with sarcasm being an important factor in the sentiment analysis results.Originality/valueThe value of this paper lies in its multi-method examination of online privacy concerns in light of the recent regulatory legislation (i.e. General Data Protection Regulation and California Consumer Privacy Act) and changes for third-party cookies in browsers such as Firefox, Safari and Chrome. Two alternatives proposed to replace third-party cookies (Privacy Sandbox and Unified ID 2.0) are in the proposal and prototype stage. The elimination of third-party cookies will affect stakeholders, including different types of players in the AdTech industry and internet users. This paper analyzes how two alternative proposals for privacy control align with the interests of several stakeholders.

Reactance and turbulence: examining the cognitive and affective antecedents of ad blocking

PurposeOne of the most effective tools used by interactive marketers is personalized advertising, which allows consumers to directly respond to customized offers to purchase a brand’s products and services. Yet, recent studies show many consumers are installing ad blockers to avoid personalized ads. This study aims to examine how ad skepticism, ad relevance and ad irritation predict ad avoidance directly, as well as indirectly through consumers’ attitudes toward personalized advertising. Also, considered were how these antecedents’ study in tandem to trigger consumers’ desire to avoid ads by installing ad-blocking software.Design/methodology/approachAn online survey was administered to a pool of 1,313 paid panelists who were familiar with ad blocking and reported that they either currently used an ad blocker, previously used an ad blocker, were considering using an ad blocker or did neither use nor were they considering using an ad blocker. All hypotheses were addressed via path modeling using PROC CALIS in SAS 9.4.FindingsResults indicate that attitudes toward personalized advertising are more complex than attitudes toward advertising in general and mediate the effect of ad relevance on ad avoidance. Likewise, trust in interactive marketers moderates attitude toward personalized advertising and the negative outcomes of ad avoidance and ad blocker usage among skeptical consumers. Also, the reported differences in ad avoidance based on participants’ current vs previous ad blocker usage suggest that former users are using a more sophisticated evaluation of the costs and benefits of using ad blockers.Practical implicationsConsumers’ trust in an interactive marketer to properly collect and use their information plays an important role in moderating negative outcomes associated with personalized advertising. Also, the key is the use of high-quality data (best obtained through a permission-based relationship with the consumer) to deliver relevant ads without stimulating reactance or (privacy-related) boundary turbulence. Findings suggest that bolstering trust by engaging in a transparent, permission-based relationship with consumers may mitigate the tendency to adopt ad blockers and enhance the effectiveness of interactive marketing efforts.Originality/valueAd blocking presents a significant threat to the effectiveness of interactive marketing efforts like personalized advertising. Previous research on the antecedents of ad blocking is limited, considers a broad range of factors and offers mixed findings. The present study examines an informed set of cognitive and affective factors suggested by previous ad blocking studies to predict consumers’ desire to avoid personalized ads by installing ad-blocking software. Given the continued threat to the interactive marketing industry posed by ad blocking, a greater understanding of consumers’ motivations to adopt and use ad blockers is critical.

A privacy‐preserving mobile location‐based advertising system for small businesses

AbstractSmall‐to‐medium businesses are always seeking affordable ways to advertise their products and services securely. With the emergence of mobile technology, it is possible than ever to implement innovative Location‐Based Advertising (LBS) systems using smartphones that preserve the privacy of mobile users. In this paper, we present a prototype implementation of such systems by developing a distributed privacy‐preserving system, which has parts executing on smartphones as a mobile app, as well as a web‐based application hosted on the cloud. The mobile app leverages Google Maps libraries to enhance the user experience in using the app. Mobile users can use the app to commute to their daily destinations while viewing relevant ads such as job openings in their neighborhood, discounts on favorite meals, etc. We developed a client‐server privacy architecture that anonymizes the mobile user trajectories using a bounded perturbation strategy. A multi‐modal sensing approach is proposed for modeling the context switching of the developed LBS system, which we represent as a Finite State Machine model. The multi‐modal sensing approach can reduce the power consumed by mobile devices by automatically detecting sensing mode changes to avoid unnecessary sensing. The developed LBS system is organized into two parts: the business side and the user side. First, the business side allows business owners to create new ads by providing the ad details, Geo‐location, photos, and any other instructions. Second, the user side allows mobile users to navigate through the map to see ads while walking, driving, bicycling, or quietly sitting in their offices. Experimental results are presented to demonstrate the scalability and performance of the mobile side. Our experimental evaluation demonstrates that the mobile app incurs low processing overhead and consequently has a small energy footprint.

Click, click, ad: the proportion of relevant (vs. irrelevant) ads matters when advertising within paginated online content

Applying the ad-context congruence framework, priming theory, and associative network of memory model, two experimental studies (N1 = 445; N2 = 449) investigated the effects of displaying different proportions of thematically relevant and irrelevant ads in online paginated stories on brand recognition memory (sensitivity and criterion bias), ad and brand evaluations, ad clicking intentions, and brand purchase intentions. Studies 1 and 2 found that the brands advertised in context-irrelevant ads were recognized better than the brands advertised in context-relevant ads. Encoding of irrelevant ads was associated with a conservative criterion bias, especially when these ads were presented in the condition with the high proportion of relevant ads. Ratio of relevant to irrelevant ads affected recognition of these ad types differently. Attitudes and behavioral intentions toward relevant ads were more positive than toward irrelevant ads. Theoretical implications of the study are connected to the advancement of the two-dimensional construct of thematic ad-context congruence. Practical implications are discussed in relation to paginated web formats, contextual advertising, and programmatic buying.

Intelligent Tutoring System for the Impact Analysis and Assessment of Online Ads and Intuitive Online Ad Serving

Real-time ad personalization is a major research area in modern marketing. According to Ecommerce Europe, 90% of offline shoppers say that personalized ads play a big role in their decisions to buy, while 51% of buyers would share their personal details if that would mean they see only relevant ads equated to information in the consumer’s mind. The idea of this research is to explore neuroadvertising by integrating research methods and to develop ViNeRS, a new method, and system. The ViNeRS method can process big data and offers automated online tips on ways to make ads more effective. Well-targeted ads can make businesses more efficient, help save resources, attract more users, and create opportunities for faster expansion. The researchs aim is to create the Intelligent tutoring system for the impact analysis and assessment of online ads and intuitive online ad serving, which will analyze and assess the impact of online ads (unfinished ad content), the efficiency of ads at each stage of their creation, determine their advantages and disadvantages, improve them until the most catchy version is achieved, enables integrated assessment of neurobiological viewer response and can make real-time selection of the most effective ad option. The system will be able to determine how many times a promotional message should be repeated in a certain part of your video to achieve an effective promotional campaign.

Opinion Mining, Sentiment Analysis and Emotion Understanding in Advertising: A Bibliometric Analysis

In the last decade, the advertising industry has experienced a quantum leap, powered by recent advances in neuroscience, a large investment in artificial intelligence, and a high degree of consumer expertise. Within this context, opinion mining, sentiment analysis, and emotion understanding bring us closer to one of the most sought-after objectives of advertising: to offer relevant ads at scale. The importance of studies about opinion mining, sentiment analysis, and emotion understanding in advertising has been rising exponentially over the last years. The peak of this new situation has been the interest of the research community in studying the relationship between such innovations and the spread of smart and contextual advertising. This article analyzes those works that address the relationship between sentiment analysis, opinion mining, and emotion understanding in advertising. The main objective is to clarify the current state of these studies, explore issues, methods, findings, themes, and gaps as well as to define their significance within the current convergence advertising research scenario. To reach such objectives, a bibliometric analysis was conducted, retrieving and analyzing 919 research works published between 2010 and 2019 based on results from Web of Science (WoS).

Identifying Short-term Interests from Mobile App Adoption Pattern

With the increase in an average user’s dependence on their mobile devices, the reliance on collecting user’s browsing history from mobile browsers has also increased. This browsing history is highly utilized in the advertising industry for providing targeted ads in the purview of inferring user’s short-term interests and pushing relevant ads. However, the major limitation of such an extraction from mobile browsers is that browsing history gets reset when the browser is closed or when the device is shut down/restarted; thus rendering existing methods for identification of user’s short-term interests on mobile devices, ineffective. In this paper, we propose an alternative method to identify such short-term interests by analysing user’s mobile app adoption (installation/uninstallation) patterns over a period of time. Such a method can be highly effective in pinpointing the user’s ephemeral inclinations like buying/renting an apartment, buying/selling a car or a sudden increased interest in shopping (possibly due to a recent salary bonus, he received). Subsequently, these derived interests are also used for targeted experiments. Our experiments result in up to 93.68% higher click-through rate in comparison to the ads shown without any user-interest knowledge. Also, up to 51% higher revenue in the long term is expected as a result of the application of our proposed algorithm.

Um 'Cartapácio' na "Gazeta de Lisboa Occidental". A "Arte Explicada" (1729-1734) de João de Morais Madureira Feijó (1688-1741)

A Orthografia, ou Arte de Escrever, e Pronunciar com acerto a Lingua Portugueza (1734) do ortógrafo setecentista Madureira Feijó é, sem dúvida, uma das obras metaortográficas mais importantes do século XVIII. No entanto, não se pode considerar uma obra independente, visto que há indícios de que ela faz parte do conjunto da obra neoalvaresiana do mesmo autor que se tornou famosa sob o título Arte Explicada. No âmbito do presente artigo, pretendemos analisar os anúncios relevantes publicados na Gazeta de Lisboa Occidental, entre 1729 e 1734, visando provar que a Orthografia de Feijó constitui a quarta e última parte da primeira edição da Arte Explicada, publicada ao longo de seis tomos na tipografia lisboeta de Miguel Rodrigues.

Processing Long Queries Against Short Text

Many real applications in real-time news stream advertising call for efficient processing of long queries against short text. In such applications, dynamic news feeds are regarded as queries to match against an advertisement (ad) database for retrieving the k most relevant ads. The existing approaches to keyword retrieval cannot work well in this search scenario when queries are triggered at a very high frequency. To address the problem, we introduce new techniques to significantly improve search performance. First, we devise a two-level partitioning for tight upper bound estimation and a lazy evaluation scheme to delay full evaluation of unpromising candidates, which can bring three to four times performance boosting in a database with 7 million ads. Second, we propose a novel rank-aware block-oriented inverted index to further improve performance. In this index scheme, each entry in an inverted list is assigned a rank according to its importance in the ad. Then, we introduce a block-at-a-time search strategy based on the index scheme to support a much tighter upper bound estimation and a very early termination. We have conducted experiments with real datasets, and the results show that the rank-aware method can further improve performance by an order of magnitude.

Utilizing Verbal Intent in Semantic Contextual Advertising

Existing semantic approaches to contextual advertising effectively match relevant ads to webpages in terms of topical intent. The authors observe, however, that there's still much room for improvement. In this article, they seek to utilize the verbal intent, which complements topical intent, in semantic contextual advertising. Verbal intent describes what a user wants to do, that is, the action perspective, with topical intent. The authors propose a methodology that effectively identifies verbal intent in webpages and ads, and then incorporates the verbal intent into an ad-ranking framework. The results of performance evaluation on real-world datasets clearly show the efficacy of (verb, topic) associations. Compared with state-of-the-art techniques, the proposed methodology exhibits a significant improvement of precision at a high level of recall in ad ranking, as well as a precision improvement of 35 percent on average in verb identification.

Associations between Culturally Relevant Recruitment Strategies and Participant Interest, Enrollment and Generalizability in a Weight-loss Intervention for African American Families.

Culturally relevant recruitment strategies may be an important approach for recruiting ethnic minorities for interventions. Previous research has examined associations between recruitment strategies and enrollment of African Americans (AA), but has not explored more deeply the role of incorporating sociocultural values into recruitment strategies. Our current study explores whether sociocultural recruitment mediums were associated with demographics, interest and enrollment in a weight-loss intervention. Sociocultural mediums included community partnerships, culturally relevant ads, sociocultural events, or word-of-mouth. Non-sociocultural mediums included community/school events that did not specifically target AAs. Analyses examined whether demographics of enrolled families differed by recruitment strategy and if recruitment strategy predicted scheduling a baseline visit, enrolling in a run-in phase, and enrolling in the intervention program. Families recruited from culturally relevant ads, sociocultural events, or word-of-mouth were 1.96 times more likely to schedule a baseline visit (OR=1.96, 95% CI=1.05, 3.68) than families recruited from non-sociocultural mediums. No differences were found for sociocultural mediums on enrolling in the run-in phase or the intervention. However, among enrolled families, those recruited from sociocultural mediums were less likely to be employed (X(2) [1, N=142] =5.53, P<.05) and more likely to have lower income (X(2) [1, N=142] =13.57, P<.05). Sociocultural mediums were associated with scheduling a baseline visit, but not enrollment. They were, however, effective in recruiting a more generalizable sample among enrolled participants based on demographic characteristics. Integrating sociocultural values into recruitment methods may be a valuable strategy for increasing interest in participation among underrepresented AA families.