We apply the Natural Semantic Metalanguage (NSM) approach (Goddard & Wierzbicka 2014) to the lexi... more We apply the Natural Semantic Metalanguage (NSM) approach (Goddard & Wierzbicka 2014) to the lexical-semantic analysis of English evaluational adjectives and compare the results with the picture developed in the Appraisal Framework (Martin & White 2005). The analysis is corpus-assisted, with examples mainly drawn from film and book reviews, and supported by collocational and statistical information from WordBanks Online. We propose NSM explications for 15 evaluational adjectives, arguing that they fall into five groups, each of which corresponds to a distinct semantic template. The groups can be sketched as follows: " First-person thought-plus-affect " , e.g. wonderful; " Experiential " , e.g. entertaining; " Experiential with bodily reaction " , e.g. gripping; " Lasting impact " , e.g. memorable; " Cognitive evaluation " , e.g. complex, excellent. These groupings and semantic templates are compared with the classifications in the Appraisal Framework's system of Appreciation. In addition, we are particularly interested in sentiment analysis, the automatic identification of evaluation and subjectivity in text. We discuss the relevance of the two frameworks for sentiment analysis and other language technology applications.
Page 1. Deciding on Units of Analysis within Centering Theory ∗ ... In this paper, we use the ter... more Page 1. Deciding on Units of Analysis within Centering Theory ∗ ... In this paper, we use the term 'utterance' or 'segment' to refer to the units of analysis in Centering Theory. In other applications, 'segment' refers to the broad parts into which a ...
Evaluation in political discourse addressed to women: Appraisal analysis of Cosmopolitan's coverage of the 2014 US midterm elections. Discourse, Context and Media.
Before the US midterm elections of November 2014, the well-known women's magazine Cosmopolitan de... more Before the US midterm elections of November 2014, the well-known women's magazine Cosmopolitan decided to include politics in its contents. The editorial board stated that their aim was to encourage readers to vote and to be engaged with women's rights advocay in the election process. To that end, Cosmopolitan created a new website, CosmoVotes, with content ranging from discussion of political issues to endorsement of specific candidates who were believed to advance women's issues. Topics include labour rights, abortion, contraception, health, minimum wage and social equity. This paper evaluates the discourse of this new section of the Cosmopolitan website, together with readers' responses, concentrating on evaluative language. In particular, we are concerned with differences between the editorial position and readers' responses as viewed through the Appraisal framework (Martin & White, 2005), and the role that verbal processes play in the expression of evaluative meanings. The corpus used for the analysis consists of a selection of articles and readers' opinions from CosmoVotes. The methodology is based on annotation of Appraisal Canada mtaboada@sfu.ca 2 features and processes related to the interpersonal dimension of meaning. Those features reveal how attitudes are evaluated and capture ideological positionings in this discourse. Our results show that CosmoVotes has special characteristics, such as a predominance of high intensification in the readers' opinions, and strong negative judgements and expressions, while the magazine's pieces on political issues are more nuanced and eschew intensification.
Contrastive analyses of evaluation in text: Key issues in the design of an annotation system for attitude applicable to consumer reviews in English and Spanish
Explaining why the same passage may have different rhetorical structures when conveyed in differe... more Explaining why the same passage may have different rhetorical structures when conveyed in different languages remains an open question. Starting from a trilingual translation corpus, this paper aims to provide a new qualitative method for the comparison of rhetorical structures in different languages and to specify why translated texts may differ in their rhetorical structures. To achieve these aims we have carried out a contrastive analysis, comparing a corpus of parallel English, Spanish and Basque texts, using Rhetorical Structure Theory (RST). We propose a method to describe the main linguistic differences among the rhetorical structures of the three languages in the two annotation stages (segmentation and rhetorical analysis). We show a new type of comparison that has important advantages with regard to the quantitative method usually employed: it provides an accurate measurement of interannotator agreement, and it pinpoints sources of disagreement among annotators. With the use of this new method, we show how translation strategies affect discourse structure.
We describe the initial stages of a project tracking the literary reputation of authors. The obje... more We describe the initial stages of a project tracking the literary reputation of authors. The objective of our research is to extract information on the reputation of different authors, based on writings concerning the authors. The project, a collaboration involving researchers in the Departments of English and Linguistics at Simon Fraser University, aims to create a database of texts, and computational tools to extract content automatically. It is in its initial stages, dealing with data collection and the construction of tools to extract sentiment from texts. In this paper, we will present the current state of the system, and illustrate it with some examples. * To be presented at the Meeting of the Society for Digital Humanities. Vancouver, June 2008.
We describe the initial stages of a project tracking the literary reputation of authors. The obje... more We describe the initial stages of a project tracking the literary reputation of authors. The objective of our research is to extract information on the reputation of different authors, based on writings concerning the authors. The project, a collaboration involving researchers in the Departments of English and Linguistics at Simon Fraser University, aims to create a database of texts, and computational tools to extract content automatically. It is in its initial stages, dealing with data collection and the construction of tools to extract sentiment from texts. In this paper, we will present the current state of the system, and illustrate it with some examples. * To be presented at the Meeting of the Society for Digital Humanities. Vancouver, June 2008.
The initial stages of a project tracking the literary reputation of authors are described. The cr... more The initial stages of a project tracking the literary reputation of authors are described. The critical reviews of six authors who either rose to fame or fell to obscurity between 1900 and 1950 will be examined and we hope to demonstrate the contribution of each text to the evolving reputations of the authors. We provide an initial report on the use of the semantic orientation of adjectives and their rough position in the text to calculate the overall orientation of the text and suggest ways in which this calculation can be improved. Improvements include further development of adjective lists, expansion of these lists and the consequent algorithms for calculating orientation to include other parts of s peech, and the use of Rhetorical Structure Theory to differentiate units that make a direct contribution to the intended orientation from those that are contrastive or otherwise make an indirect contribution.
The initial stages of a project tracking the literary reputation of authors are described. The cr... more The initial stages of a project tracking the literary reputation of authors are described. The critical reviews of six authors who either rose to fame or fell to obscurity between 1900 and 1950 will be examined and we hope to demonstrate the contribution of each text to the evolving reputations of the authors. We provide an initial report on the use of the semantic orientation of adjectives and their rough position in the text to calculate the overall orientation of the text and suggest ways in which this calculation can be improved. Improvements include further development of adjective lists, expansion of these lists and the consequent algorithms for calculating orientation to include other parts of s peech, and the use of Rhetorical Structure Theory to differentiate units that make a direct contribution to the intended orientation from those that are contrastive or otherwise make an indirect contribution.
In multimodal documents, different types of cohesive or cross-reference link (i.e., signaling) ar... more In multimodal documents, different types of cohesive or cross-reference link (i.e., signaling) are used in the text to link verbally coded content with the graphical material. In this study, we identify three types of reference, within the framework of previous work on cohesion : directive signaling, descriptive signaling, and no signaling in the text to introduce the figure. In an experimental study, we use eye tracking to investigate how those three reference types influence the processing of the material by humans. The results reveal differences between the reference types both in terms of eye movement parameters and retention of the material.
We present a lexicon-based approach to extracting sentiment from text. The Semantic Orientation C... more We present a lexicon-based approach to extracting sentiment from text. The Semantic Orientation CALculator (SO-CAL) uses dictionaries of words annotated with their semantic orientation (polarity and strength), and incorporates intensification and negation. 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 on completely unseen data. Additionally, we describe the process of dictionary creation, and our use of Mechanical Turk to check dictionaries for consistency and reliability.
Uploads
Papers by Maite Taboada