This paper describes the new multimodal SWELL knowledge work (SWELL-KW) dataset for research on stress and user modeling. The dataset was collected in an experiment, in which 25 people performed typical knowledge work (writing reports, making presentations, reading e-mail, searching for information). We manipulated their working conditions with the stressors: email interruptions and time pressure. A varied set of data was recorded: computer logging, facial expression from camera recordings, body postures from a Kinect 3D sensor and heart rate (variability) and skin conductance from body sensors. The dataset made available not only contains raw data, but also preprocessed data and extracted features. The participants' subjective experience on task load, mental effort, emotion and perceived stress was assessed with validated questionnaires as a ground truth. The resulting dataset on working behavior and affect is a valuable contribution to several research fields, such as work psychology, user modeling and context aware systems.

Large language models (LLMs) with billions of parameters exhibit in-context learning abilities, enabling few-shot learning on tasks that the model was not specifically trained for. Traditional models achieve breakthrough performance on language tasks, but do not perform well on basic reasoning benchmarks. However, a new in-context learning approach, Chain-of-thought, has demonstrated strong multi-step reasoning abilities on these benchmarks. The research on LLM reasoning abilities started with the question whether LLMs can solve grade school math word problems, and has expanded to other tasks in the past few years. This article reviews the field of multi-step reasoning with LLMs. We propose a taxonomy that identifies different ways to generate, evaluate, and control multi-step reasoning. We provide an in-depth coverage of core approaches and open problems, and we propose a research agenda for the near future. We find that multi-step reasoning approaches have progressed beyond math word problems, and can now successfully solve challenges in logic, combinatorial games, and robotics, sometimes by first generating code that is then executed by external tools. Many studies in multi-step methods use reinforcement learning for finetuning, external optimization loops, in-context reinforcement learning, and self-reflection.

Life expectancy is one of the most important factors in end-of-life decision making. Good prognostication for example helps to determine the course of treatment and helps to anticipate the procurement of health care services and facilities, or more broadly: facilitates Advance Care Planning. Advance Care Planning improves the quality of the final phase of life by stimulating doctors to explore the preferences for end-of-life care with their patients, and people close to the patients. Physicians, however, tend to overestimate life expectancy, and miss the window of opportunity to initiate Advance Care Planning. This research tests the potential of using machine learning and natural language processing techniques for predicting life expectancy from electronic medical records. We approached the task of predicting life expectancy as a supervised machine learning task. We trained and tested a long short-term memory recurrent neural network on the medical records of deceased patients. We developed the model with a ten-fold cross-validation procedure, and evaluated its performance on a held-out set of test data. We compared the performance of a model which does not use text features (baseline model) to the performance of a model which uses features extracted from the free texts of the medical records (keyword model), and to doctors’ performance on a similar task as described in scientific literature. Both doctors and the baseline model were correct in 20% of the cases, taking a margin of 33% around the actual life expectancy as the target. The keyword model, in comparison, attained an accuracy of 29% with its prognoses. While doctors overestimated life expectancy in 63% of the incorrect prognoses, which harms anticipation to appropriate end-of-life care, the keyword model overestimated life expectancy in only 31% of the incorrect prognoses. Prognostication of life expectancy is difficult for humans. Our research shows that machine learning and natural language processing techniques offer a feasible and promising approach to predicting life expectancy. The research has potential for real-life applications, such as supporting timely recognition of the right moment to start Advance Care Planning.

Research on pharmacovigilance from social media data has focused on mining adverse drug events (ADEs) using annotated datasets, with publications generally focusing on 1 of 3 tasks: ADE classification, named entity recognition for identifying the span of ADE mentions, and ADE mention normalization to standardized terminologies. While the common goal of such systems is to detect ADE signals that can be used to inform public policy, it has been impeded largely by limited end-to-end solutions for large-scale analysis of social media reports for different drugs. We present a dataset for training and evaluation of ADE pipelines where the ADE distribution is closer to the average ‘natural balance’ with ADEs present in about 7% of the tweets. The deep learning architecture involves an ADE extraction pipeline with individual components for all 3 tasks. The system presented achieved state-of-the-art performance on comparable datasets and scored a classification performance of F₁ = 0.63, span extraction performance of F₁ = 0.44 and an end-to-end entity resolution performance of F₁ = 0.34 on the presented dataset. The performance of the models continues to highlight multiple challenges when deploying pharmacovigilance systems that use social media data. We discuss the implications of such models in the downstream tasks of signal detection and suggest future enhancements. Mining ADEs from Twitter posts using a pipeline architecture requires the different components to be trained and tuned based on input data imbalance in order to ensure optimal performance on the end-to-end resolution task.

The field of science mapping has shown the power of citation-based clusters for literature analysis, yet this technique has barely been used for information retrieval tasks. This work evaluates the performance of citation-based clusters for information retrieval tasks. We simulated a search process with a tree hierarchy of clusters and a cluster selection algorithm. We evaluated the task of finding the relevant documents for 25 systematic reviews. Our evaluation considered several trade-offs between recall and precision for the cluster selection. We also replicated the Boolean queries self-reported by the systematic reviews to serve as a reference. We found that citation-based clusters’ search performance is highly variable and unpredictable, that the clusters work best for users that prefer recall over precision at a ratio between 2 and 8, and that the clusters are able to complement query-based search by finding additional relevant documents.

Purpose: Peer support is an important unmet need among adolescent and young adult (AYA) cancer patients. This study was conducted to describe the use and evaluation of a Dutch secure online support community for AYA diagnosed with cancer between 18 and 35 years. Methods: User statistics were collected with Google analytics. Community members were asked to complete questionnaires on the usefulness of the community. A content analysis using Linguistic Inquiry and Word Count was conducted. Results: Between 2010 and 2017, the community received 433 AYA members (71% female; mean age at diagnosis 25.7 years; 52 Dutch hospitals represented). The mean time since diagnosis when subscribing to the community was 2.7 years (SD 4.4). Questionnaire data among 30 AYA community members indicated that the use of the community resulted in acknowledgment and advice regarding problems (56%) and the feeling of being supported (63%). Almost half of the respondents felt less lonely, 78% experienced recognition in stories of other AYA. Anonymized content analysis (n=14) showed that the majority of the online discussions encompassed emotional and cognitive expressions, and emotional support. Conclusion: The secure Dutch online AYA community can help AYA cancer patients to express feelings, exchange information, address peer support, and has been found helpful in coping with cancer. As AYA cancer patients often lack the option of meeting each other in person, the AYA community is helpful in establishing peer support. Its use would benefit from promotion by health care professionals.