You are here
Drs. Alexander Hogenboom
My name is Alexander Hogenboom and I hold both a Bachelor of Science degree and a cum laude Master of Science degree in Economics and Informatics, with a specialization in Computational Economics. I am currently employed as a PhD student at Erasmus University Rotterdam in the Netherlands, where I perform my research within the Econometric Institute. In the context of my current position, I am additionally affiliated to the research center for Business Intelligence at the Erasmus Research Institute of Management. Moreover, in the context of my research activities related to my PhD project, I am also affiliated to Erasmus Studio. Please take a look around on this page in order to find out more about my research endeavors, my publications, as well as my related activities.
In general, my research interests all relate to the utilization of methods and techniques from informatics and computer science for facilitating or supporting decision making processes. This has evolved from research related to semantic information systems (mash-ups, query optimization), while obtaining my Bachelor of Science degree, to research in the field of decision support systems (dynamic pricing), while obtaining my Master of Science degree. In the context of my current PhD research, my main interests have shifted more towards intelligent systems for information extraction, or more specifically for tracking and monitoring of (economic) sentiment.
The recent turmoil in the financial markets has once again demonstrated how crucial it is for decision makers to identify issues and patterns that matter and to track and predict emerging events. A key element for decision makers to track here is their stakeholders' sentiment. Investor sentiment influences financial markets. Consumer sentiment influences how people spend their money. In general, decision makers have to understand what is going on in their domains and, more specifically, what is driving their stakeholders. What do people think about the economy? About products? Brands? Companies? And where does this sentiment come from?
Nowadays, the Web allows users to produce an ever-growing amount of virtual utterances of opinions in reviews, blogs, tweets, and so on. This yields a massive amount of data, containing traces of valuable information - people's sentiment with respect to products, brands, etcetera. This information can be extracted from textual data by means of sentiment analysis techniques. Typically, the goal of such techniques is to (semi-)automatically determine the polarity of natural language texts.
An intuitive approach here would involve scanning a text for cues signaling its polarity, e.g., positive or negative words. However, when doing so, we may be ignoring important information: the information conveyed by structural aspects of a piece of natural language text. For instance, a conclusion may play a different role in conveying the overall sentiment of a text than a piece of contrasting information does.
Therefore, the goal of my PhD research project is to advance the state-of-the-art of sentiment mining by developing and utilizing models, methods, and algorithms for harvesting the information conveyed by structural aspects of natural language text. This research is linked to the Argumentation Discovery in Economics Literature project of the Erasmus Research Institute of Management. This work is carried out in the context of the Semantic Scholarly Publishing project of Erasmus Studio as well. Last, I also perform my research in the context of the COMMIT Infiniti project on Information Retrieval for Information Services, work package three.