User Modeling for Privacy-preserving Explanations in Group Recommendations

My thesis investigates what makes good explanations for group recommendations, considering the privacy concerns of group members. Let’s give an example. Have you ever been to lunch with other colleagues on a business trip? Do you recall how long it took you to pick a restaurant? In these situations, recommender systems could help people decide,...

Examining the Effectiveness of Collaborative Search Engines

Conversational Crowdsourcing

Crowdsourcing has become a standard approach for the collection of the human input required by scientists and practitioners alike to execute their experiments, or to train, control, and verify the behavior of their intelligent systems. Despite years of successful research and industrial application, how to improve the engagement and satisfaction...

Semantic-Enhanced Training Data Augmentation Methods for Long-Tail Entity Recognition Models

Named Entity Recognition (NER) is an essential information retrieval task. It enables a wide range of natural language processing applications such as semantic search, machine translation, etc. The NER can be formulated as the task of identifying and typing words or phrases in a text that refers to certain classes of interest (e.g., disease,...

Large-Scale Learning Analytics: Modeling Learner Behavior & Improving Learning Outcomes in Massive Open Online Courses

MOOC Analytics: Learner Modeling and Content Generation

Massive Open Online Courses (MOOCs), as one of the popular options for people to receive education and learn, are endowed with the mission to educate the world. Typically, there are two types of MOOC platforms: topic-agnostic and topic-specific. Topic-agnostic platforms such as edX and Coursera provide courses covering a wide range of topics,...

Learning Analytics Technology to Understand Learner Behavioral Engagement in MOOCs

As one of the most prominent examples of technology-enhanced learning, massive open online courses (MOOCs) have attracted extensive attention of learners, educators, and researchers since 2012. However, a low completion rate is a ubiquitous and severe problem in MOOCs, which means that only a small portion of learners got scores higher than or...

Crowd Knowledge Creation Acceleration

Crowd knowledge creation plays a central role in many types of Web based information systems, ranging from community question-answering (CQA) systems (e.g. StackOverflow and Quora) to micro-task crowdsourcing systems (e.g. Amazon mTurk and CrowdFlower). In these systems, knowledge demands are generally fulfilled by means of tasks (e.g. questions...

Social Web Data Analytics: Relevance, Redundancy, Diversity

In the past decade, the Social Web has evolved into both an essential channel for people to exchange information and a new type of mass media. The immense amount of data produced presents new possibilities and challenges: algorithms and technologies need to be developed to extract and infer useful information from the Social Web. One of the main...

User Modeling and Personalization in the Microblogging Sphere

Microblogging has become a popular mechanism for people to publish, share, and propagate information on the Web. The massive amount of digital traces that people have left in the microblogging sphere, creates new possibilities and poses challenges for user modeling and personalization. How can microblogging activities be exploited to infer...

Towards Contextualized Information Delivery: A Rule-based Architecture for the Domain of Mobile Police Work

An increasing number of mobile users demand adaptive services tailored to their specific requirements in a particular situation. Typically, when carrying out the task at hand, police officers need to have up-to-date information contextualized to their current situation in order to support their decision making. In contrast to the traditional...