Recommending online resources to patients with ovarian cancer and their caregivers is a challenging task. On one hand, the recommended items must be relevant, recent, and reliable. On the other hand, they need to match the user’s levels of disease-specific health literacy. In this demonstration, we describe the overall architecture and key components of HELPeR, a knowledge-adaptive interactive recommender system for ovarian cancer patients and their caregivers.

No abstract available.

Chronic disease patients, such as diabetics, cancer patients, and heart disease patients, actively seek health information for self-management and decision-making every single day. Patient focused health recommender systems (PHRSs) that suggest health information relevant to patients' changing needs, assists them with easy information accessibility. Nevertheless, patients' needs become more complex with disease progression and their increased knowledge about disease. Hence, a unique requirement of the PHRS would be to suggest health information in line with patients' changing knowledge about the disease. However, current PHRS are personalized to patient interest and don't consider their knowledge about disease. By providing patients with information tailored at their knowledge-level, they not only are more likely to understand and engage better in disease management, but can use PHRS for disease related learning. Hence, the overarching goal of my PhD thesis is to explore technologies in the field of recommender systems and personalized learning for the purpose of suggesting health information that accounts for patients' dynamic information needs and level of knowledge about disease. We will explore these ideas in the context of developing a knowledge-appropriate PHRS (KA-PHRS ). A critical innovation of KA-PHRS is the patient knowledge model that keeps track of patients' changing knowledge-level about disease and enables knowledge-appropriate recommendations. The expectation is that health information suggested by KA-PHRS will increase as well as benefit patients' involvement in self management and treatment.Chronic disease patients, such as diabetics, cancer patients, and heart disease patients, actively seek health information for self-management and decision-making every single day. Patient focused health recommender systems (PHRSs) that suggest health information relevant to patients' changing needs, assists them with easy information accessibility. Nevertheless, patients' needs become more complex with disease progression and their increased knowledge about disease. Hence, a unique requirement of the PHRS would be to suggest health information in line with patients' changing knowledge about the disease. However, current PHRS are personalized to patient interest and don't consider their knowledge about disease. By providing patients with information tailored at their knowledge-level, they not only are more likely to understand and engage better in disease management, but can use PHRS for disease related learning. Hence, the overarching goal of my PhD thesis is to explore technologies in the field of recommender systems and personalized learning for the purpose of suggesting health information that accounts for patients' dynamic information needs and level of knowledge about disease. We will explore these ideas in the context of developing a knowledge-appropriate PHRS (KA-PHRS ). A critical innovation of KA-PHRS is the patient knowledge model that keeps track of patients' changing knowledge-level about disease and enables knowledge-appropriate recommendations. The expectation is that health information suggested by KA-PHRS will increase as well as benefit patients' involvement in self management and treatment.

Patients with chronic diseases, such as diabetes, cancer, and heart disease, actively participate in disease management and seek health information on a constant basis for decision-making and self management. Patient focused health recommender systems (PHRSs) that suggest health information relevant to patients’ changing information needs across their disease trajectory can provide significant help to patients as they manage their disease on a day-to-day basis. A unique requirement of the PHRS would be to suggest health information in line with patients’ changing knowledge about the disease. It is crucial to recognize that patient knowledge of the disease may change as they become more actively involved in understanding and self-managing the illness. By providing patients with appropriate information, they are more likely to not only understand and engage, but also learn. Hence, the purpose of this doctoral thesis is to explore technologies in the field of recommender systems and personalized learning for the purpose of suggesting health information that accounts for patients’ dynamic information needs and level of knowledge about disease. We will explore these ideas in the context of developing a knowledge-appropriate PHRS (KA-Recsys). As a case study, a recommender will be integrated to an existing ovarian cancer patients’ information access portal. To assess the utility of KA-Recsys, the system will be evaluated based on expert-based and patient-based feedback. The expectation is that health information suggested by KA-Recsys will increase as well as benefit patients’ involvement in self management and treatment decisions.

Different texts shall by nature correspond to different number of keyphrases.This desideratum is largely missing from existing neural keyphrase generation models.In this study, we address this problem from both modeling and evaluation perspectives.We first propose a recurrent generative model that generates multiple keyphrases as delimiter-separated sequences.Generation diversity is further enhanced with two novel techniques by manipulating decoder hidden states.In contrast to previous approaches, our model is capable of generating diverse keyphrases and controlling number of outputs.We further propose two evaluation metrics tailored towards the variable-number generation.We also introduce a new dataset (ST A C KEX) that expands beyond the only existing genre (i.e., academic writing) in keyphrase generation tasks.With both previous and new evaluation metrics, our model outperforms strong baselines on all datasets.

Massive Open Online Courses (MOOCs) often incorporate lecture-based learning along with lecture notes, textbooks, and videos to students. Moreover, MOOCs also incorporate practice activities and quizzes. Student learning in MOOCs can be tracked and improved using state-of-the-art student modeling. Currently, this means employing conventional student models that are constructed around Intelligent Tutoring Systems (ITS). Traditional ITS systems only utilize students performance interactions (quiz, problem-solving or practice activities). Therefore, text interactions are entirely ignored while modeling students performance in MOOCs using these cognitive models. In this work, we propose a Comprehension Factor Analysis model (CFM) for online courses, which integrates student reading interactions in student models to track and predict learning outcomes. Our model evaluation shows that CFM outperforms state-of-the-art models in predicting students' performance in a MOOC. These models can help better student-wise adaptation in the context of MOOCs.

The education sector has been undergoing a welcoming change in recent years with the introduction of a wide variety of digital content openly available to students. Due to the volume of this new digital content, it is very difficult for learners to find the needed information at the right time. Digital textbooks, as well-curated domain knowledge sources, could provide a conceptual and physical platform that unites disparate educational resources as one entity. Educational resource linkage, with state-of-the-art techniques, are based on term-level and topic-level representations. However, term-level representations suffer from the term-mismatch problem and often, topics are too broad for linking to other educational resources. To address these challenges, we propose to link educational resources through concept-level representation. The proposed model generates concept embeddings by utilizing domain-specific educational content and external knowledge graph resources to achieve robust and effective concept-level representations. We conducted evaluations of the proposed models on multiple contents linking tasks, and the results demonstrate that concept-level representations perform better than the state-of-the-art representations in helping students to find more learning resources easily. This could increase both students' learning and satisfaction.