MoCSSy Program: Graduate Student Seminar Series "Building and using Fuzzy Cognitive Maps" and "A lexicon-based approach to sentiment analysis"
Abstract
TITLE: Building and using Fuzzy Cognitive Maps
ABSTRACT: A fuzzy cognitive map (FCM) was introduced by Kosko as a modelling approach that is easily understandble by experts of a particular domain, and can incorporate imprecision. We will first provide a selected review of the literature by looking at successful uses of FCMs in radiotherapy treatment and brain tumor characterization. Then, we will give an overview of the importance of FCMs within the research currently done at MoCSSy. The second part of this talk will be devoted to outlining the key steps to build an FCM using a large number of research articles. In particular, we will show how sentences are extracted and assigned a weight, which highlights the need for automatization of text processing.
TITLE: A lexicon-based approach to sentiment analysis
ABSTRACT: Sentiment analysis is the automatic extraction of information about opinion and subjectivity from text and speech. In this talk, we describe our current research in sentiment analysis. The Semantic Orientation CALculator (SO-CAL) uses dictionaries of words annotated with their semantic orientation (polarity and strength), and incorporates intensification and negation. We describe the process of dictionary creation, and our use of Mechanical Turk to check dictionaries for consistency and reliability. SO-CAL is applied to the polarity classification task, the process of assigning a positive or negative label to a text that captures the text's opinion towards its main subject matter. We show that SO-CAL's performance is consistent across domains and in completely unseen data. We also describe current research on using discourse information to improve performance.