Isa Maks

A lexicon model for deep sentiment analysis and opinion mining applications

This paper presents a lexicon model for the description of verbs, nouns and adjectives to be used in applications like sentiment analysis and opinion mining. The model aims to describe the detailed subjectivity relations that exist between the actors in a sentence expressing separate attitudes for each actor. Subjectivity relations that exist between the different actors are labeled with information concerning both the identity of the attitude holder and the orientation (positive vs. negative) of the attitude. The model includes a categorization into semantic categories relevant to opinion mining and sentiment analysis and provides means for the identification of the attitude holder and the polarity of the attitude and for the description of the emotions and sentiments of the different actors involved in the text. Special attention is paid to the role of the speaker/writer of the text whose perspective is expressed and whose views on what is happening are conveyed in the text. Finally, validation is provided by an annotation study that shows that these subtle subjectivity relations are reliably identifiable by human annotators.

Cornetto: a combinatorial lexical semantic database for Dutch

One of the goals of the STEVIN programme is the realisation of a digital infrastructure that will enforce the position of the Dutch language in the modern information and communication technology.A semantic database makes it possible to go from words to concepts and consequently, to develop technologies that access and use knowledge rather than textual representations.

From text to political positions: The convergence of political, linguistic and discourse analysis

Abstract: This chapter explores how three methods of political text analysis can complement each other to differentiate parties in detail. A word-frequency method and corpus linguistic techniques are joined by critical discourse analysis in an attempt to assess the ideological relation between election manifestos and a coalition agreement. How does this agreement relate to the policy positions presented in individual election manifestos and whose issues appear on the governmental agenda? The chapter discusses the design of three levels of text analysis applying text-as-data analysis; words-as-meaningful-data involving lexical-semantic analysis of subjectivity; and words-in-context analysis for variation in constructions of worldviews. We found that better results can be achieved for party positioning in combinations of qualitative and quantitative approaches.

Unshared Task at the 3rd Workshop on Argument Mining: Perspective Based Local Agreement and Disagreement in Online Debate

This paper proposes a new task in argument mining in online debates. The task includes three annotations steps that result in fine-grained annotations of agreement and disagreement at a propositional level. We report on the results of a pilot annotation task on identifying sentences that are directly addressed in the comment.

Storyteller: Visualizing Perspectives in Digital Humanities Projects

Humanities scholars agree that the visualization of their data should bring order and insight, reveal patterns and provide leads for new research questions. However, simple two-dimensional visualizations are often too static and too generic to meet these needs. Visualization tools for the humanities should be able to deal with the observer dependency, heterogeneity, uncertainty and provenance of data and the complexity of humanities research questions. They should furthermore offer scholars the opportunity to interactively manipulate their data sets and queries. In this paper, we introduce Storyteller, an open source visualization tool designed to interactively explore complex data sets for the humanities. We present the tool, and demonstrate its applicability in three very different humanities projects.

HEEM, a Complex Model for Mining Emotions in Historical Text

Recently, emotions and their history have become a focus point for research in different academic fields. Traditional sentiment analysis approaches generally try to fit relatively simple emotion models (e.g., positive/negative emotion) to contemporary data. However, this is not sufficient for Digital Humanities scholars who are interested in research questions about changes in emotional expressions over time. Answering these questions requires more complex, historically accurate emotion models applied to historical data. The Historic Embodied Emotion Model (HEEM) was developed to study the relationship between body parts and emotional expressions in 17th and 18th century texts. This paper presents the HEEM emotion model and associated dataset from a technical perspective, and examines the performance of a multi-label text classification approach for predicting HEEM labels and labels from two simpler models (i.e., HEEM Emotion Clusters and the Positive/Negative model). The results show that labels in the complex model can be predicted with micro-averaged F1 = 0.45, and macro-averaged F1 = 0.24. Labels with fewer samples (<; 40) are not predicted. Overall performance on the simpler emotion models is significantly better, but for individual labels the effect is mixed. We demonstrate that a multi-label text classification approach to learning complex emotion models on historical data is feasible.