K.I.M. Schouten (Kim)

Contact details

Email address
Erasmus University Rotterdam, Campus Woudestein
3062 PA

Mail address: Erasmus University Rotterdam, Room W-H8-09 P.O. Box 1738, 3000 DR Rotterdam, The Netherlands 

Role in Erasmus Studio: Researcher in COMMIT/Infiniti (subproject: Time-Based Aspect-Level Sentiment Analysis)

Kim Schouten is a PhD candidate at the Erasmus University Rotterdam, currently working in the Time-Based Aspect-Level Sentiment Analysis project (see below).  Although his educational background is in Economics and Informatics, in which he holds both a Bachelor and Master degree, he is truly fascinated by the phenomenon of language. It is remarkable how we humans are able to employ language to achieve our goals, ranging from things as mundane as shopping, chatting, or reading a newspaper, to politics, philosophy, art, and science. This fascination has led him to focus both Bachelor and Master thesis on natural language processing with a twist towards practical economic applications. The paradox that drives his research is the fact that while even children are already very proficient in using language, the most sophisticated machine by far does not approximate that basic level of functionality. How can it be that we are wired to process language so efficiently, but are not able to wire a machine to do the same? 

Time-Based Aspect-Level Sentiment Analysis (TALSA)

(funded within the FES-programme COMMIT, as one of the tracks in the project Infiniti

With opinions and expressions of sentiment available in abundance on the Web, algorithms that can deal with this kind of subjective information abound. While several approaches exist that perform aspect-level sentiment analysis, which associates the expressed sentiment to aspects and entities instead of linguistic constructs like sentences or documents, the temporal dimension is still lacking. By incorporating the temporal aspect of sentiment, we can correctly aggregate sentiment expressed at varying points in time and perform trend analysis by looking at how sentiment changes over time. The main goal is to gather sentiment information from the Web and aggregate it into knowledge that is useful for business applications such as product marketing, product comparison, or reputation management of a company, brand, or person. Our hypothesis is that an incremental, online machine learning model is particularly well suited to capture these temporal elements in addition to performing aspect-level sentiment analysis as defined in the current literature.