Vacancies

PhD position in Epsilon Lab

PhD studentship opening on "Representing diverse views for polarized topics online". This is a project with IBM Benelux, funded by CLICK_NL. Email Nava Tintarev (n.tintarev@tudelft.nl) with informal queries.

Decision making at individual, business, and societal level is influenced by online content. Filtering and ranking algorithms are used to support these decisions, but currently does not represent a diversity of viewpoints.

What are needed are models informed by theory and experimentation, that support decision makers in building a comprehensive understanding of complex topics. 

While a lot of attention has been devoted to the algorithmic aspects of diverse content selection, how the interaction between people and content affects decision making is studied very limited. One reason is that decisions are highly subjective and polarized by personal interpretation and the meaning that people impose, thus making it difficult to devise interfaces that can appropriately adapt the level of control and type of visualization.

In this project, we aim at increasing our understanding of how adaptive user interfaces can be designed to represent polarized topics online. Specifically, we are interested in studying diversity, in terms of source, topic, and linguistic features (e.g., named entities, sentiment, authenticity, clout). We will research novel metrics for diversity assessment and compare these to perceived notions of diversity using complex content exploration interfaces. To account for the amount and diversity of subjective and personal experiences, we rely on crowd computing techniques specifically devised to elicit which kinds of UI control and transparency is suitable for different users.

The diversity metric and exploration interfaces will be evaluated using both offline and online studies. To ensure the generalizability of the approach, the evaluations will be conducted in several domains. From an enterprise perspective, we will consider medical and financial content, to address scenarios where perceptions of diversity are shaped by organizational and business concerns. From a societal perspective, we will consider articles on polarized topics such as global warming and vaccination.

 

 

PhD position at Lambda-Lab (IR, NLP, data science)

See Lambda-Lab.

Postdoc: (Big) Data Management with focus on Scalable ML and Stream Analytics

Position Duration: Two years with possibility of extension.Expected start date: ASAP

Job Description: We are seeking a motivated postdoctoral researcher to work on data management with applications to scalable machine learning and/or stream analytics, in the context of the Delft Data Science (DDS) institute. DDS has strong ties to both academia and industry. Postdoctoral researchers at DDS will be expected to publish papers in top venues, to take part in international collaborations with companies and research institutes, seek funding, and lead the development of open-source software.

The ideal candidate is an ambitious researcher who has recently obtained a PhD in the broad area of databases/data management, distributed systems, or machine learning, with publications in the top venues of their field. We seek candidates who love putting their research results into practice and are open to investigate new research directions.

How to apply: In order to apply please send your CV to Asterios Katsifodimos (Assistant Professorl) and Geert-Jan Houben (Full Professor and head of the Web Information Systems group) prefixing the email subject with [DDS Postdoc Application - data management].

Vacancies connected to data science & Delft Data Science

See Delft Data Science.