Large-scale Wizard-Of-Oz dialogue datasets have enabled the training of deep learning-based dialogue systems. While they are successful as benchmark datasets, they lack certain types of utterances, which would make them more realistic. In this work, we investigate the creation of synthetic communication errors in an automatic pipeline. Based on linguistic theory, we propose and follow a simple error taxonomy. We focus on three types of miscommunications that could happen in real-world dialogues but are underrepresented in the benchmark dataset: misunderstandings, non-understandings and vaguely related questions. Our two-step approach uses a state-of-the-art Large Language Model (LLM) to first create the error and secondly the repairing utterance. We perform Language Model-based evaluation to ensure the quality of the generated utterances. We apply the method to the MultiWOZ dataset and evaluate it both qualitatively and empirically as well as with human judges. Our results indicate that current LLMs can aid in adding post-hoc miscommunications to benchmark datasets as a form of data augmentation. We publish the resulting dataset, in which nearly 1900 dialogues have been modified, as CoPrUS-MultiWOZ to facilitate future work on dialogue systems.

While it is often assumed that searching for information to evaluate misinformation will help identify false claims, recent work suggests that search behaviours can instead reinforce belief in misleading news, particularly when users generate queries using vocabulary from the source articles. Our research explores how different query generation strategies affect news verification and whether the way people search influences the accuracy of their information evaluation. A mixed-methods approach was used, consisting of three parts: (1) an analysis of existing data to understand how search behaviour influences trust in fake news (2) a simulation of query generation strategies using a Large Language Model (LLM) to assess the impact of different query formulations on search result quality, and (3) a user study to examine how 'Boost' interventions in interface design can guide users to adopt more effective query strategies. The results show that search behaviour significantly affects trust in news, with successful searches involving multiple queries and yielding higher-quality results. Queries inspired by different parts of a news article produced search results of varying quality, and weak initial queries improved when reformulated using full SERP information. Although 'Boost' interventions had limited impact, the study suggests that interface design encouraging users to thoroughly review search results can enhance query formulation. This study highlights the importance of query strategies in evaluating news and proposes that interface design can play a key role in promoting more effective search practices, serving as one component of a broader set of interventions to combat misinformation.

Indoor navigation systems for pedestrians require floor plans of buildings. Acquiring them is costly and time-consuming, as the standard procedure is to digitise 2D blueprints and augment them with information required for navigating users. In this demo, as an alternative, we use the Holo Lens 2 to construct floor plans on site. We illustrate how to construct plans that are as accurate as digitised blueprints, but much more efficient to acquire and easier to augment with information about the physical environment that is impossible to obtain from blueprints.

High-quality training data for Task-Oriented Dialog (TOD) systems is costly to come by if no corpora are available. One method to extend available data is data augmentation. Yet, the research into and adaptation of data augmentation techniques for TOD systems is limited in comparison with other data modalities. We propose a novel, causally-flavored data augmentation technique called Counterfactual Dialog Mixing (CDM) that generates realistic synthetic dialogs via counterfactuals to increase the amount of training data. We demonstrate the method on a benchmark dataset and show that a model trained to classify the counterfactuals from the original data fails to do so, which strengthens the claim of creating realistic synthetic dialogs. To evaluate the effectiveness of CDM, we train a current architecture on a benchmark dataset and compare the performance with and without CDM. By doing so, we achieve state-of-the-art on some metrics. We further investigate the external generalizability and a lower resource setting. To evaluate the models, we adopted an interactive evaluation scheme.

As conversational search becomes more pervasive, it becomes increasingly important to understand the users’ underlying information needs when they converse with such systems in diverse domains. We conduct an in situ study to understand information needs arising in a home cooking context as well as how they are verbally communicated to an assistant. A human experimenter plays this role in our study. Based on the transcriptions of utterances, we derive a detailed hierarchical taxonomy of diverse information needs occurring in this context, which require different levels of assistance to be solved. The taxonomy shows that needs can be communicated through different linguistic means and require different amounts of context to be understood. In a second contribution, we perform classification experiments to determine the feasibility of predicting the type of information need a user has during a dialogue using the turn provided. For this multi-label classification problem, we achieve average F1 measures of 40% using BERT-based models. We demonstrate with examples which types of needs are difficult to predict and show why, concluding that models need to include more context information in order to improve both information need classification and assistance to make such systems usable.

Schematic maps are often discussed as an adequate alternative of displaying wayfinding information compared to detailed map designs. However, these depictions have not yet been compared and analyzed in-depth. In this paper, we present a user study that evaluates the wayfinding behaviour of participants either using a detailed floor plan or a schematic map that only shows the route to follow and landmarks. The study was conducted in an indoor real-world scenario. The depictions were presented with the help of a mobile navigation system. We analyzed the time it took to understand the wayfinding instruction and the workload of the users. Moreover, we examined how the depictions were visually perceived with a mobile eye tracker. Results show that wayfinders who use the detailed map spend more visual attention on the instructions. Nevertheless, the depiction does not help to solve the task: they also needed more time to orient themselves. Regarding the workload and the wayfinding errors no differences were found.

Many smartphone-based indoor positioning systems rely on pedestrian dead reckoning for fine-grained position tracking. In this paper, we show how one of its major shortcomings - the accumulation of errors over time - can be effectively overcome in a navigation setting by detecting door transitions along the route. Using only the sensors included in a handheld smartphone and different on-device machine learning techniques, door transitions can be classified correctly in up to 86% of all cases. The system runs in real-time on current smartphones and - when integrated into our baseline particle filter - improves overall positioning performance significantly, as the subsequent evaluation on a realistic navigation data set shows. A detailed analysis of several edge cases illustrates the concept and provides insights into the remaining challenges.

HealthRecSys 2019 was the 4th International Workshop on Health Recommender Systems held in conjunction with the 2019 ACM Conference on Recommender Systems in Copenhagen, Denmark. This workshop followed on from of the previous workshop in 2018 [4] and focused on the application and potentials of recommender systems on health promotion, health care and health-related topics. By engaging the discussion and representation of health domains into recommender systems, this workshop facilitated the cross-domain collaborations and exchange of knowledge and infrastructure.

The 3rd International Workshop on Health Recommender Systems was held in conjunction with the 2018 ACM Conference on Recommender Systems in Vancouver, Canada. Following the two prior workshops in 2016 [4] and 2017 [2], the focus of this workshop is to deepen the discussion on health promotion, health care as well as health related methods. This workshop also aims to strengthen the HealthRecSys community, to engage representatives of other health domains into cross-domain collaborations, and to exchange and share infrastructure.

The 2017 Workshop on Health Recommender Systems was held in conjunction with the 2017 ACM Conference on Recommender Systems in Como, Italy. Following the fists workshop in 2016, the focus of this workshop was on enhancing the results of the first workshop by elaborating discussions on the topics, attracting scientist from other domains, finding cross-domain collaboration, and establishing shared infrastructures.

This paper focuses on the analysis of socio-spatial data, i. e., user-performance relations at a distributed event. We consider the data as a bimodal network (i. e., model it as a bipartite graph), and investigate its structural characteristics towards a social network. We focus on plans of the participants (expressed by preferences) and their fulfilment, and propose measures for matching preference and reality. We specifically analyse behavioural patterns w.r.t. distinct user and performance groups. We utilise real-world data collected at the Lange Nacht der Musik (Long Night of Music) 2013 in Munich.

Research examining pedestrian navigation systems that use landmarks to explain routes became popular in the past years. Nevertheless, it is still an open question how many landmarks should be depicted at once. In this paper a user study is presented that evaluates two different indoor navigation system designs that depict either one (N = 63) or four (N = 60) landmarks to guide the user. The time it took the participants to recognize where to go was captured as a dependent variable. Results show that the interface only depicting one landmark leads to faster self-localization. Therefore, it is argued that a pedestrian navigation system should mainly depict one highly salient landmark in a navigation instruction in order to keep navigation efficiency high.

The first Workshop on Engendering Health with Recommender Systems was organized in conjunction with ACM RecSys 2016. The focus of the workshop was on bringing together researchers and practitioners from diverse areas of health, well-being, decision support, and behavioral change. Health-related issues in recommender systems have been a growing research topic in the recent years and this was a initial attempt at bringing together academics and practitioners to share their experiences on working on related issues.

In this paper we propose an augmented reality (AR) based assistance system for reliably teaching the assembly process of printed circuit boards (PCB) to workers by using a smart glass running a self-developed software. The system is operated freehand by looking at QR-Codes and highlights a component's retrieval location and installation point in the user's field of vision by using four markers. A study executed in a production line of an Electronics Manufacturing Services (EMS)-company resulted in an errorless performance of each individual participant who was equipped with the system. This paper describes the related work, concept and implementation of the software as well as the conducted study and its results. Finally a conclusion summarizes the success of the system and hints at future work.

Efficient human-computer-interaction is a key to success for navigation systems, in particular when pedestrians are using them. Due to the increasing computational power of recent mobile devices, complex multimedia user interfaces to pedestrian navigation systems can be implemented. In order to be able to provide the best-suited interface to each user, we present a user study comparing not only three map presentation modes (bird's eye, egocentric and a combined one), but also involving the users' sense of direction as a second independent factor. In the experiment conducted, we did not focus on a global navigation task, but on the repeated subtask of locating objects on the map. ANOVA analysis of the task completion time revealed a significant interaction effect of presentation mode and the sense of direction of the test persons. Consequently, we advocate user-adaptive presentation modes for pedestrian navigation systems.

The workshop on Recommendation Technologies for Lifestyle Change will be an opportunity for discussing open issues, and propose technical solutions for the designing of intelligent information systems that can support and promote lifestyle change. The objective of these systems is to provide users with up-to-date information, and help them to make choices in every day life activities establishing a sustainable compromise between quality of life, individuality, and fun.

Research on context aware recommender systems is taking for granted that context matters. But, often attempts to show the influence of context have failed. In this paper we consider the problem of quantitatively assessing context relevance. For this purpose we are assuming that users can imagine a situation described by a contextual feature, and judge if this feature is relevant for their decision making task. We have designed a UI suited for acquiring such information in a travel planning scenario. In fact, this interface is generic and can also be used for other domains (e.g., music). The experimental results show that it is possible to identify the contextual factors that are relevant for the given task and that the relevancy depends on the type of the place of interest to be included in the plan.

Day hospital workflows are highly dynamic. It is, therefore, important to provide patients with timely information about their next activity, where it takes place, and when it starts. In this paper we present MobiDay, a novel mobile service integrated in the hospital information system that supports patients and clinicians in a day hospital scenario. We describe the MobiDay message-posting algorithm that uses context-aware rules provided by clinicians to decide the time and content of the guidance messages sent to the patient's device. MobiDay was tested with real patients during a 4-months-long experiment held in the hospital of Meran in South Tyrol, Italy. Here we report on the system evaluation results. Moreover, we discuss the pros and cons of MobiDay design choices and propose some general guidelines for the development of effective message-based mobile guidance services for patients.

Context aware recommender systems (CARS) adapt the recommendations to the specific situation in which the items will be consumed. In this paper we present a novel context-aware recommendation algorithm that extends Matrix Factorization. We model the interaction of the contextual factors with item ratings introducing additional model parameters. The performed experiments show that the proposed solution provides comparable results to the best, state of the art, and more complex approaches. The proposed solution has the advantage of smaller computational cost and provides the possibility to represent at different granularities the interaction between context and items. We have exploited the proposed model in two recommendation applications: places of interest and music.

A major problem of understanding language in spoken dialog systems is to detect recognition errors in the output of a speech recognizer. Such a capability is the basis of implementing repair strategies that allow a dialog system to handle communication about misunderstandings similarly to other clarifications. In this paper we present a two-phase approach that combines chunk and dependency parsing and takes the global syntactic structure of recognizer output into account. This enables us to identify dependencies between chunks and detect syntactical errors caused by word confusions in case dependency constraints are violated. Finally, we apply these diagnostics to dialog modeling and discuss how the resulting error information can be used by clarification strategies.

This paper presents an approach to exploit free text descriptions of TV programmes as available from EPG data sets for a TV recommender system that takes the content of programmes into account. The paper focuses on the natural language understanding problem underlying the analysis of free text descriptions and on methods of classifying free text descriptions with respect to a natural language user query. We close with an evaluation of user acceptance and a discussion of future work.