Umeå University's logo

As privacy concerns increase and regulation against tracking-based advertisingtightens, contextual advertising—which targets ads based on webpage content ratherthan personal data—offers a compelling alternative. The shift towards this alternativeform of ad targeting is gaining momentum thanks to advancements in artificialintelligence (AI), which significantly improve the ability to interpret and categorizeonline content. This thesis explores how AI can interpret online contexts and leveragethem for targeted, privacy-conscious marketing.A key contribution is the development of methods for extracting opinions from textand structuring them into “opinion units”, leveraging the power and versatility oflarge language models. Opinion units consist of concise, context-rich excerpts thatcapture individual opinions, paired with sentiment metadata. The proposed methodsdemonstrate high accuracy in opinion extraction and show promise for downstreamapplications. For instance, in opinion search and topic modeling of customer reviews,the compactness and distinctness of opinion units enhance retrieval precision andproduces more coherent and interpretable groupings of opinions. This enables theidentification of specific aspects driving customer satisfaction, providing insights forproduct development and targeted marketing.Marketing experiments conducted in this thesis reveal how media contexts influenceadvertising perceptions. The findings demonstrate that engaging content and thecredibility of website sources create a spillover effect, enhancing the effectiveness ofassociated ads. Regarding brand safety—ensuring ads do not appear in brand-damaging contexts—the results suggest that proximity to negative news articles aloneis not directly harmful. However, marketers face increased risks when the advertisedmessage is associated with the negative context. To mitigate these risks, AI tools canbe used to detect and avoid potentially unsafe online environments.Finally, the thesis offers guidance on AI-driven ad targeting by outlining the trade-offsbetween contextual and personalized strategies, as well as manual versus automatedmethods. The discussion considers key factors such as marketing objectives, dataavailability, and ethical considerations alongside regulatory requirements. Thefindings serve as a foundation for making well-informed, strategic choices in thefuture of advertising targeting.

We introduce opinion units, a contribution to the field Aspect-Based Sentiment Analysis (ABSA) that extends aspect- sentiment pairs by including substantiating excerpts, derived through hybrid abstractive-extractive summarisation. The goal is to provide fine-grained information without sacrificing succinctness and abstraction. Evaluations on review datasets demonstrate that large language models (LLMs) can accurately extract opinion units through few-shot learning. The main types of errors are providing incomplete contexts for opinions and and mischaracterising objective statements as opinions. The method reduces the need for labelled data and allows the LLM to dynamically define aspect types. As a practical evaluation, we present a case study on similarity search across academic datasets and public review data. The results indicate that searches leveraging opinion units are more successful than those relying on traditional data-segmentation strategies, showing robustness across datasets and embeddings.

In programmatic advertising, bids are increasingly based on knowledge of the surrounding media context. This shift toward contextual advertising is in part a counter-reaction to the current dependency on personal data, which is problematic from legal and ethical standpoints. The transition is accelerated by developments in artificial intelligence (AI), which allow for a deeper semantic analysis of the context and, by extension, more effective ad placement. We survey existing literature on the influence of context on the reception of an advertisement, focusing on three context factors: the applicability of the content and the ad, the affective tone of the content, and the involvement of the consumer. We then discuss how AI can leverage these priming effects to optimize ad placement through techniques such as reinforcement learning, data clustering, and sentiment analysis. This helps close the gap between the state of the art in advertising technology and the AI-driven targeting methodologies described in prior academic research.

This article contributes to research on media-context effects by studying how ads are assessed when positioned alongside news articles that evoke negative emotions in readers. We find that in general, negative emotion does not influence advertising evaluation. Contrary to industry claims, the perceived source credibility of the news site is not found to moderate the effects of negative content. However, on its own, the credibility of the news site improves ad evaluations. Furthermore, high applicability between article and ad can enhance ad recognition and produce a weak negative effect on attitudes towards ads and brands. Our results provide evidence against the industry practice of avoiding negative news due to concerns over spill-over effects. Marketers should focus advertising to credible news sites and, when appropriate, avoid negative articles with high applicability to the advertised product and brand.

Due to limitations on the use of third-party cookies as well as privacy and ethical concerns fromusing personal data for online advertising, many advertisers are compelled to explore alternativestrategies. Contextual advertising has emerged as a viable alternative to sustain relevance. We studythe underlying mechanisms behind personalized and contextual advertising effects on consumptionintentions and ad recall using an online controlled experiment, survey questions, and structuralequation modelling. Our study advances existing research on contextual effects by disentangling theinfluence of ad-context congruence and context involvement. We showcase how consumers’involvement in contexts serves as an indicator for consumer interest in specific topics, which can beleveraged by contextual advertisements for improved consumption intentions. In contrast toprevious research which we contend does not properly account for context involvement, we find nomain effect of ad-context congruence on intention. Regarding ad recall, we show that engagingcontext reduces recall of adjacent ads and that ad-context congruence increases the likelihood thatads go entirely unnoticed. For advertisers, our findings underscore the importance of personalrelevance for advertising effectiveness. Furthermore, they suggest that placing ads in deliberatelyselected contexts is beneficial, as positive content attitudes spill over to consumption intentions.

Artificial intelligence (AI) is revolutionizing the field of programmatic digital marketing. This article provides a forward-looking perspective on AI in advertising and offers a conceptual framework for developing effective marketing strategies. We explore key developments in the industry: the progression from personalized to contextual targeting, and the increased reliance on AI-based automation. Additionally, the article identifies three critical factors – results, resources, and rectitude – that influence the choice of strategies for online advertisers. Our findings suggest that while AI might multiply the effectiveness of programmatic advertising campaigns, it comes with important tradeoffs that must be taken into account. By synthesizing literature from digital advertising, computer science, and media studies, we offer an improved understanding of the evolving programmatic advertising ecosystem and distill this into practical advice for advertisers.

We improve the extraction of insights from customer reviews by adding an LLM preprocessing step to the traditional topic-modeling pipeline. This step segments reviews into opinion units — distinct opinions with relevant text excerpts and sentiment scores. The result is a heightened performance of the subsequent topic modeling, leading to coherent and interpretable topics while also capturing the sentiment associated with each topic. By correlating the topics and sentiments with business metrics, such as star ratings, we can gain insights on how specific customer concerns impact business outcomes. We present our system’s implementation, use cases, and advantages over other topic modeling and classification solutions. We also evaluate its effectiveness in creating coherent topics and assess methods for integrating topic and sentiment modalities for accurate star-rating prediction.