From SEO to AEO for Optimizing LLM Output in E-commerce Applications

Motives: Research on search engine optimisation (SEO) usually focuses on commercial websites, with limited attention to public sector platforms like geoportals. The impact of SEO on their online visibility and Local SEO quality remains understudied, which presents a research gap worth exploring.Aim: This study evaluates the SEO quality of selected municipal geoportals using Large Language Models (LLMs). It examines how well these portals are optimised for search engines and whether AI tools can effectively support SEO auditing.Results: Audits of five geoportals using tools like ChatGPT, Copilot, Gemini, and Perplexity revealed low SEO support from public administrations, poor link building, and weak metadata. Referring domains and quality indicators were limited. Moreover, AI tools do not conduct real-time audits, which restricts their accuracy and usefulness for detailed SEO assessments.

PurposeKnowledge graphs (KGs) are structured knowledge bases that represent real-world entities and are used in a variety of applications. Many of them are created and curated from a combination of automated and manual processes. Microdata embedded in Web pages for purposes of facilitating indexing and search engine optimization are a potential source to augment KGs under some assumptions of complementarity and quality that have not been thoroughly explored to date. In that direction, this paper aims to report results on a study that evaluates the potential of using microdata extracted from the Web to augment the large, open and manually curated Wikidata KG for the domain of touristic information. As large corpora of Web text is currently being leveraged via large language models (LLMs), these are used to compare the effectiveness of the microdata enhancement method.Design/methodology/approachThe Schema.org taxonomy was used as the source to determine the annotation types to be collected. Here, the authors focused on tourism-related pages as a case study, selecting the relevant Schema.org concepts as point of departure. The large CommonCrawl resource was used to select those annotations from a large recent sample of the World Wide Web. The extracted annotations were processed and matched with Wikidata to estimate the degree to which microdata produced for SEO might become a valuable resource to complement KGs or vice versa. The Web pages themselves can also serve as a context to produce additional metadata elements using them as context in pipelines of an existing LLMs. That way, both the annotations and the contents itself can be used as sources.FindingsThe samples extracted revealed a concentration of metadata annotations in only a few of the relevant Schema.org attributes and also revealed the possible influence of authoring tools in a significant fraction of microdata produced. The analysis of the overlapping of attributes in the sample with those of Wikidata showed the potential of the technique, limited by the disbalance of the presence of attributes. The combination of those with the use of LLMs to produce additional annotations demonstrates the feasibility of the approach in the population of existing Wikidata locations. However, in both cases, the effectiveness appears to be lower in the cases of less content in the KG, which are arguably the most relevant when considering the scenario of an automated population approach.Originality/valueThe research reports novel empirical findings on the way touristic annotations with a SEO orientation are being produced in the wild and provides an assessment of their potential to complement KGs, or reuse information from those graphs. It also provides insights on the potential of using LLMs for the task.

The paper explores how results from traditional search engines, such as Google and Bing, differ from those generated by large language model (LLM) – based tools, including ChatGPT, Gemini, and Perplexity. It examines whether the established principles of Search Engine Optimisation (SEO) still influence outcomes in generative systems, a process referred to here as Generative Engine Optimisation (GEO). Using identical keyword and natural language queries, the study compares the consistency and character of retrieved information across platforms. Findings indicate only partial overlap between traditional and generative systems. Search engines prioritise factual accuracy and relevance, while LLMs tend to provide broader, interpretative responses shaped by user intent. These differences suggest that generative AI is reshaping search behaviour and the ways people access and evaluate information online. The paper highlights implications for marketing communication and the adaptation of SEO strategies in AI-driven environments.

UNIVERSITY OF LUCKNOW FROM SEARCH TO SMART

Entity Resolution (ER) is the problem of semi-automatically determining when two entities refer to the same underlying entity, with applications ranging from healthcare to e-commerce. Traditional ER solutions required considerable manual expertise, including domain-specific feature engineering, as well as identification and curation of training data. Recently released large language models (LLMs) provide an opportunity to make ER more seamless and domain-independent. Because of LLMs’ pre-trained knowledge, the matching step in ER can be made easier by just prompting. However, it is also well known that LLMs can pose risks, that the quality of their outputs can depend on how prompts are engineered, and that the cost of using LLMs can be significant. Unfortunately, a systematic experimental study on the effects of different prompting methods and their respective cost for solving domain-specific entity matching using LLMs, like ChatGPT, has been lacking thus far. This paper aims to address this gap by conducting such a study. We consider some relatively simple and cost-efficient ER prompt engineering methods and apply them to perform product matching on two real-world datasets widely used in the community. We select two well-known e-commerce datasets and provide extensive experimental results to show that an LLM like GPT3.5 is viable for high-performing product matching and, interestingly, that more complicated and detailed (and hence, expensive) prompting methods do not necessarily outperform simpler approaches. We provide brief discussions on qualitative and error analysis, including a study of the inter-consistency of different prompting methods to determine whether they yield stable outputs. Finally, we consider some limitations of LLMs when used as a product matcher in potential real-world e-commerce applications.

Recently, multimodal sentiment analysis (MSA) has gained significant traction due to its wide-range of applications in social media monitoring, healthcare, e-commerce, content creation, and business research. Unlike classical unimodal approaches, MSA integrates verbal and non-verbal characteristics such as text, speech, facial expressions, gestures, and physiological signals to enable a comprehensive understanding of human sentiments, particularly in human–computer interaction systems. Despite several existing reviews, many either focus on limited modalities or overlook the latest advancements, such as transformer-based and large language models (LLMs). This review presents a comprehensive and critical overview of MSA, with an integrated modalities, fusion techniques, classification, and current research in joint embedding and LLMs. It performs a comparative assessment of benchmark corpora, metrics, and model performance. The study also provides a critical analysis of current methods, highlighting their strengths, limitations, and future directions in the field. It also extends the discussion to practical applications and long-standing issues, which will frame the future research agenda in MSA. The Literature was carefully reviewed and selected from top academic databases using systematic search strategies. This survey aims to help researchers, students, and practitioners understand the history of MSA's development over the years and explore current research directions in the rapidly emerging field.

Conversational recommender systems have emerged as a promising approach to enhancing user experience in e-commerce by enabling interactive and personalized product discovery. This paper proposes a conversational recommender system for e-commerce that employs retrieval-augmented generation (RAG) to improve product recommendations based on natural language queries. Experiments were conducted using the ESCI-S dataset, an enriched version of the Amazon ESCI shopping queries dataset, to evaluate embedding models and large language models. The goal of this study is to assess the effectiveness of an RAG-based conversational recommender system and to identify optimal configurations for enhanced performance in e-commerce applications.

In e-commerce, product descriptions and other forms of copywriting play a critical role in shaping consumer purchasing decisions. However, manually crafting such content is both time-consuming and costly, particularly given the vast and diverse item catalogs. Recent advances in large language models (LLMs) have transformed automated text generation, offering immense potential to streamline this process. Despite their capabilities, LLMs continue to face obstacles in e-commerce applications, including a lack of diversity and an inability to fully grasp the nuanced details of specific items. To address these limitations, we propose a novel framework that integrates graph-based knowledge into Retrieval-Augmented Generation (RAG) to enhance content generation. Our approach leverages user reviews to construct an item-feature graph, capturing both explicit and implicit connections between items and features. This structured representation enables the retrieval of diverse, contextually relevant, and factually grounded information, effectively addressing key deficiencies of existing methods. With the constructed graph, we design a graph traversal mechanism that explores a broader range of item-related features, augmenting the generation process with more varied and informative inputs. Extensive experiments demonstrate that our method significantly improves diversity while preserving fidelity, marking a major advancement in automated e-commerce content generation.

Rise of generative Artificial Intelligence (AI) and Large Language Models (LLMs) has significantly transformed Search Engine Optimization (SEO) strategies and tactics. This study presents a quantitative analysis among digital professionals, assessing the effectiveness of on-page SEO, technical SEO, user engagement metrics and off-page SEO in optimizing a website for better ranking and visibility in AI and LLM-generated search results. Using statistical analysis, we evaluate the impact of traditional SEO tactics in new AI environment applications visibility. The results demonstrate that semantic keyword usage, content quality and structured data, remain critical for AI-driven search rankings. Findings also reveal a significant shift toward user engagement metrics, which AI models prioritize to assess content relevance and quality. Results offer actionable insights for digital marketers and webmasters seeking to optimize their websites for Generative AI and LLMs.

Symbolic AI has been facing long-term adoption obstacles and a slow uptake caused by the limited availability of frictionless tooling—that can support not only knowledge engineers, but also novice users and educators, with designing and presenting graph exemplars that can be visually communicated, edited and ad hoc processed. There’s still a shortage of tools that can democratize knowledge graph (KG) creation, something that is increasingly needed—firstly by educators trying to discuss examples with novices without stumbling on OWL jargon at the earliest step, but also for more recent integration cases such as (i) GraphRAG, where private KGs are called to augment or ensure factuality of large language model services; or (ii) in search engine optimization (SEO), where SEO practitioners lacking knowledge engineering background must embed Schema.org graph data into their Web content. Most visual KG tools are visualizers of KGs created by other means—either in OWL-centric ontology editors posing high expertise barriers, or converted from available serializations, or lifted from legacy data sources. The few actual KG editors are mostly OWL editors neglecting to support the creation of schemaless graph datasets as well as of flexible combinations of graph data and schema fragments. This paper reports on a Design Science effort adopting metamodeling means, traditionally employed for the engineering of domain-specific modeling languages, toward defining a KG development and integration method that facilitates both the visual design of KG exemplars and their operationalization. We aim to balance a diagrammatic look and feel with machine readability of the semantic content being produced—further streamlined in an architecting proposition for integration with LLM services and for the production of Schema.org graph snippets. The DSML was deployed and evaluated as a tool implemented on the ADOxx metamodeling platform, using RDF and LangChain as mediators that streamline the content toward triplestores and LLM services.

We introduce VARM, variant relationship matcher strategy, to identify pairs of variant products in e-commerce catalogs. Traditional definitions of entity resolution are concerned with whether product mentions refer to the same underlying product. However, this fails to capture product relationships that are critical for e-commerce applications, such as having similar, but not identical, products listed on the same webpage or share reviews. Here, we formulate a new type of entity resolution in variant product relationships to capture these similar e-commerce product links. In contrast with the traditional definition, the new definition requires both identifying if two products are variant matches of each other and what the attributes are that vary between them. To satisfy these two requirements, we developed a strategy that leverages the strengths of both encoding and generative AI models. First, we construct a dataset that captures webpage product links, and therefore variant product relationships, to train an encoding large language model (LLM) to predict variant matches for any given pair of products. Second, we use retrieval-augmented generation-prompted generative LLMs to extract variation and common attributes amongst groups of variant products. To validate our strategy, we evaluated model performance using real data from one of the world's leading e-commerce retailers. The results showed that our strategy outperforms alternative solutions and paves the way to exploiting these new types of product relationships.

The utilization of sentiment analysis has gained significant importance as a valuable method for obtaining meaningful insights from textual data. The research progress in languages such as English and Chinese has been notable. However, there is a noticeable dearth of attention towards creating tools for sentiment analysis in the Bangla language. Currently, datasets are limited for Bangla sentiment analysis, especially balanced datasets capturing both binary and multiclass sentiment for e-commerce applications. This paper introduces a new sentiment analysis dataset from the popular Bangladeshi e-commerce site “Daraz”. The dataset contains 1000 reviews across 5 product categories, with both binary (positive/negative) and multiclass (very positive, positive, negative, very negative) sentiment labels manually annotated by native Bangla speakers. Reviews were collected using an organized process, and labels were assigned based on standardized criteria to ensure accuracy. In addition, a benchmark evaluation of the performance achieved by Machine Learning and Deep Learning algorithms on this dataset is also provided. The new dataset can aid research on multiclass and binary Bangla sentiment analysis utilizing both machine learning, deep learning, and Large Language Models. It can aid e-commerce platforms in analysing nuanced user opinions and emotions from online reviews. The utilization of categorized product reviews also facilitates research in the field of text categorization.

In this paper, we introduce a retrieval framework designed for e-commerce applications, which employs a multi-modal approach to represent items of interest. This approach incorporates both textual descriptions and images of products, alongside a locality-sensitive hashing (LSH) indexing scheme for rapid retrieval of potentially relevant products. Our focus is on a data-independent methodology, where the indexing mechanism remains unaffected by the specific dataset, while the multi-modal representation is learned beforehand. Specifically, we utilize a multi-modal architecture, CLIP, to learn a latent representation of items by combining text and images in a contrastive manner. The resulting item embeddings encapsulate both the visual and textual information of the products, which are then subjected to various types of LSH for balancing between result quality and retrieval speed. We present the findings of our experiments conducted on two real-world datasets sourced from e-commerce platforms, comprising both product images and textual descriptions. Promising results have been achieved, demonstrating favorable retrieval time and average precision. These results were obtained through testing the approach with a specifically selected set of queries and with synthetic queries generated using a Large Language Model.

The rapid introduction of new brand names into everyday language poses a unique challenge for e-commerce spelling correction services, which must distinguish genuine misspellings from novel brand names that use unconventional spelling.We seek to address this challenge via Retrieval Augmented Generation (RAG).On this approach, product names are retrieved from a catalog and incorporated into the context used by a large language model (LLM) that has been fine-tuned to do contextual spelling correction.Through quantitative evaluation and qualitative error analyses, we find improvements in spelling correction utilizing the RAG framework beyond a stand-alone LLM.We also demonstrate the value of additional finetuning of the LLM to incorporate retrieved context.

Purpose: The current study aims to identify the impact of e-commerce with digital marketing in airline reservation offices in the Republic of Iraq. The study consists of two main variables: the independent variable that included e-commerce, which consisted of four dimensions: Business-to-Business, Consumer-to-Business, and Consumer-to. - Consumer, Business-to-Government, and the dependent variable represents digital marketing, the dimensions of which are: website design, social media marketing, search engine optimization, and email marketing. Theoretical Framework: Upon on Maaroof, A. (2021) This study highlights the importance of e-commerce and digital marketing, such as booking corners during digital transactions in airline reservation offices, as well as the most important challenges facing customers and reservation offices. Design/ Methodology/ Approach: As for the practical aspect, the airline reservation offices were taken and included the governorates (Nineveh, Erbil, Dohuk, Kirkuk, Tikrit and Baghdad), and 250 questionnaires were accepted as valid questionnaires and were analyzed accordingly. To determine the relationship between the study variables, two main hypotheses and sub-hypotheses were proposed and tested using several statistical methods in Analysis of Moment Structures AMOS (V.24). Findings The results emphasize that there is a positive correlation and impact between all dimensions of e-commerce (Business-to-Business, Consumer-to-Business, Consumer-to-Consumer and Business-to-Government). The results also showed that activating the role of e-commerce has a positive impact on digital marketing at airline reservation offices in the Republic of Iraq. Research Implications: In addition, the study presented several recommendations for airline booking companies. For example, there is an increased interest in airline reservation companies to adopt the philosophy of e-commerce, as it has an impact on increasing market share, which ensures their continuity and success. Originality/Value: Originality/value: This study works to enhance the adaptation of e-commerce applications for airline reservation companies in the Republic of Iraq through customers’ use of applications, and in addition to bridging the digital divide, which is the feeling of many customers’ anxiety about using applications.