We demonstrate Cleo, a transparent and controllable conversational product advisor that addresses the challenges of opacity, unpredictability of LLMs, and the complexity of comparisons in conversational commerce. With our chatbot system, we make four contributions: First, we introduce transparency by prompting the LLM to reflect on interpreted user needs, while an auditable ranking mechanism reveals loss values per attribute, explaining ranking decisions. Second, we propose controllability through a hybrid architecture separating deterministic ranking from language generation. A ranker applies categorical filters and numeric loss functions over 3,638 product specifications. Meanwhile, a constrained LLM generates grounded descriptions constrained to catalog evidence, thus mitigating the risk of hallucinated or persuasive content. Third, we provide decision support in the form of natural-language comparisons and a highlights feature. These aim to reduce mental workload by contextualizing specifications relative to user needs. Fourth, we contribute an extensible experimental system for IR and HCI researchers, as well as practitioners of conversational search and recommendation. Unlike traditional faceted search or opaque LLM-only recommenders, our approach allows for fluid conversation while maintaining algorithmic transparency. In a live demonstration, attendees will experience information needs elicitation and reflection, conversational refinement with real-time re-ranking, inspection of per-attribute loss explanations, and AI-generated multi-item comparisons. The system aims to advance the design of transparent and controllable conversational systems that provide support for decision-making during online product search.

Conversational commerce uses digital assistants to support the search process and decision-making in e-commerce. Effective communication in these interactions can be facilitated by assistants adapting their communication style to users and supporting shared understanding. An open challenge in this context is adapting the presentation of complex product information to users with varying levels of domain knowledge. To investigate strategies for such knowledge-level adaptation, we set up a chatbot-assisted laptop search scenario. In a between-subjects experiment (n = 251), we examined novice and expert perceptions of product attribute recommendations presented as technical information only (T), or augmented with performance categories (TC), attribute explanations (TE), or both (TCE). For novices, approaches with explanations (TE, TCE) were perceived as more helpful and led to higher perceived learning than those without. Novices also rated the combined approach (TCE) more appropriate than the baseline (T) and TC in terms of information quantity, indicating that explanations are crucial to understand and benefit from performance categories. Critically, experts showed no significant differences across conditions, suggesting that providing supplementary information beneficial to novices did not detract from their experience. We distill these findings into four concrete design guidelines for inclusive text-based product advisors in technical domains: use TCE by default; keep a single inclusive interface; avoid standalone categories; and support user agency and personalize to the stated use case.

Users increasingly expect modern search systems to offer a unified interface that seamlessly retrieves information from diverse data sources and formats. However, current information retrieval (IR) evaluation benchmarks have not kept pace with this development, primarily due to the lack of test collections that represent the diversity of contemporary search domains. We address this critical gap with MIRA, a novel benchmark based on a large-scale social science search platform. MIRA is designed for category-aware ranking across heterogeneous categories – Publications, Research Data, Variables, and Instruments & Tools – within a single, unified evaluation framework. The proposed collection is distinctive in several ways: (1) it is built upon real user queries, providing a more realistic basis for evaluation; (2) it covers scholarly items from four distinct categories, enabling multi-faceted evaluation; and (3) it leverages a Large Language Model to generate topic descriptions and narratives, as well as for relevance assessment with respect to these topics, substantially reducing the labor and cost of test collection generation. We release this resource to benefit the community by providing a foundational testbed for the research on multi-faceted, category-aware, integrated, or cross-category information retrieval.

The emerging research field Search as Learning (SAL) investigates how the Web facilitates learning through modern information retrieval systems. SAL research requires significant amounts of data that capture both search behavior of users and their acquired knowledge in order to obtain conclusive insights or train supervised machine learning models. However, the creation of such datasets is costly and requires interdisciplinary efforts in order to design studies and capture a wide range of features. In this paper, we address this issue and introduce an extensive dataset based on a user study, in which 114 participants were asked to learn about the formation of lightning and thunder. Participants’ knowledge states were measured before and after Web search through multiple-choice questionnaires and essay-based free recall tasks. To enable future research in SAL-related tasks we recorded a plethora of features and person-related attributes. Besides the screen recordings, visited Web pages, and detailed browsing histories, a large number of behavioral features and resource features were monitored. We underline the usefulness of the dataset by describing three, already published, use cases.

Search systems on the Web rely on user input to generate relevant results. Since early information retrieval systems, users are trained to issue keyword searches and adapt to the language of the system. Recent research has shown that users often withhold detailed information about their initial information need, although they are able to express it in natural language. We therefore conduct a user study (N = 139) to investigate how four different design variants of search interfaces can encourage the user to reveal more information. Our results show that a chatbot-inspired search interface can increase the number of mentioned product attributes by 84% and promote natural language formulations by 139% in comparison to a standard search bar interface.

Shopping online is more and more frequent in our everyday life. For e-commerce search systems, understanding natural language coming through voice assistants, chatbots or from conversational search is an essential ability to understand what the user really wants. However, evaluation datasets with natural and detailed information needs of product-seekers which could be used for research do not exist. Due to privacy issues and competitive consequences, only few datasets with real user search queries from logs are openly available. In this paper, we present a dataset of 3,540 natural language queries in two domains that describe what users want when searching for a laptop or a jacket of their choice. The dataset contains annotations of vague terms and key facts of 1,754 laptop queries. This dataset opens up a range of research opportunities in the fields of natural language processing and (interactive) information retrieval for product search.

Throughout the search process, the user's gaze on inspected SERPs and websites can reveal his or her search interests. Gaze behavior can be captured with eye tracking and described with word-eye-fixations. Word-eye-fixations contain the user's accumulated gaze fixation duration on each individual word of a web page. In this work, we analyze the role of word-eye-fixations for predicting query terms. We investigate the relationship between a range of in-session features, in particular, gaze data, with the query terms and train models for predicting query terms. We use a dataset of 50 search sessions obtained through a lab study in the social sciences domain. Using established machine learning models, we can predict query terms with comparably high accuracy, even with only little training data. Feature analysis shows that the categories Fixation, Query Relevance and Session Topic contain the most effective features for our task.

In Interactive Information Retrieval (IIR) experiments the user's gaze motion on web pages is often recorded with eye tracking. The data is used to analyze gaze behavior or to identify Areas of Interest (AOI) the user has looked at. So far, tools for analyzing eye tracking data have certain limitations in supporting the analysis of gaze behavior in IIR experiments. Experiments often consist of a huge number of different visited web pages. In existing analysis tools the data can only be analyzed in videos or images and AOIs for every single web page have to be specified by hand, in a very time consuming process. In this work, we propose the reading protocol software which breaks eye tracking data down to the textual level by considering the HTML structure of the web pages. This has a lot of advantages for the analyst. First and foremost, it can easily be identified on a large scale what has actually been viewed and read on the stimuli pages by the subjects. Second, the web page structure can be used to filter to AOIs. Third, gaze data of multiple users can be presented on the same page, and fourth, fixation times on text can be exported and further processed in other tools. We present the software, its validation, and example use cases with data from three existing IIR experiments.

Finding relevant documents is essential for researchers of all disciplines. We investigated an approach for supporting searchers in their relevance decision in a digital library by automatically highlighting the most important keywords in abstracts. We conducted an eye-tracking study with 25 subjects and observed very different search and reading behavior which lead to diverse results. Some of the participants liked that highlighted abstracts accelerate their relevance decision, while others found that they disturb the reading flow. What many agree on is that the quality of highlighting is crucial for trust and system credibility.

As the availability and the inter-connectivity of RDF datasets grow, so does the necessity to understand the structure of the data. Understanding the topology of RDF graphs can guide and inform the development of, e.g. synthetic dataset generators, sampling methods, index structures, or query optimizers. In this work, we propose two resources: (i) a software framework (Resource URL of the framework: https://doi.org/10.5281/zenodo.2109469 ) able to acquire, prepare, and perform a graph-based analysis on the topology of large RDF graphs, and (ii) results on a graph-based analysis of 280 datasets (Resource URL of the datasets: https://doi.org/10.5281/zenodo.1214433 ) from the LOD Cloud with values for 28 graph measures computed with the framework. We present a preliminary analysis based on the proposed resources and point out implications for synthetic dataset generators. Finally, we identify a set of measures, that can be used to characterize graphs in the Semantic Web.

When users are looking for information on the Web, they show different behavior for different task types, e.g., for fact finding vs. information gathering tasks. For example, related work in this area has investigated how this behavior can be measured and applied to distinguish between easy and difficult tasks. In this work, we look at the searcher's behavior in the domain of journalism for four different task types, and additionally, for two different topics in each task type. Search behavior is measured with a number of session variables and correlated to subjective measures such as task difficulty, task success and the usefulness of documents. We acknowledge prior results in this area that task difficulty is correlated to user effort and that easy and difficult tasks are distinguishable by session variables. However, in this work, we emphasize the role of the task topic - in and of itself - over parameters such as the search results and read content pages, dwell times, session variables and subjective measures such as task difficulty or task success. With this knowledge researchers should give more attention to the task topic as an important influence factor for user behavior.

The social sciences are a broad research field with a lot of sub- and related disciplines. Accordingly, user interests in a digital library for the social sciences are manifold. In this study we analyzed nine years log data of a social science digital library to get an overview of the fields, categories, topics and detailed information needs users are interested in. Based on the log data we have built interactive visualizations which give an overview and concurrently let us look at the detailed interests of users. The underlying log data and the created visualizations are then used to analyze user interests at different hierarchical levels and on a temporal view. The results show that there are topical interests of the users in specific fields and topics of the social sciences but at the same time there exists a diversity of different information needs. Based on these findings we analyze in detail the gap between the indexing language of the system used to annotate documents and the language users apply to articulate their information needs.

In Interactive Information Retrieval (IIR) different services such as search term suggestion can support users in their search process. The applicability and performance of such services is either measured with different user-centered studies (like usability tests or laboratory experiments) or, in the context of IR, with their contribution to measures like precision and recall. However, each evaluation methodology has its certain disadvantages. For example, user-centered experiments are often costly and small-scaled; IR experiments rely on relevance assessments and measure only relevance of documents. In this work we operationalize the usefulness model of Cole et al. (2009) on the level of system support to measure not only the local effect of an IR service, but the impact it has on the whole search process. We therefore use a log-based evaluation approach which models user interactions within sessions with positive signals and apply it for the case of a search term suggestion service. We found that the usage of the service significantly often implicates the occurrence of positive signals during the following session steps.