RT Journal Article
T1 Design and validation of annotation schemas for aspect‑based sentiment analysis in the tourism sector.
A1 Moreno-Ortiz, Antonio Jesús
A1 Salles-Bernal, Soluna
A1 Orrequia-Barea, Aroa
K1 Emociones - Análisis
K1 Análisis de datos
K1 Turismo
AB The use of linguistic resources beyond the scope of language studies, e.g., commercialpurposes, has become commonplace since the availability of massive amountsof data and the development of software tools to process them. An interesting perspectiveon these data is provided by Sentiment Analysis, which attempts to identifythe polarity of a text, but can also pursue further, more challenging aims, such as theautomatic identification of the specific entities and aspects being discussed in theevaluative speech act, along with the polarity associated with them. This approach,known as aspect-based sentiment analysis, seeks to offer fine-grained informationfrom raw text, but its success depends largely on the existence of pre-annotateddomain-specific corpora, which in turn calls for the design and validation ofan annotation schema. This paper examines the methodological aspects involved inthe creation of such annotation schema and is motivated by the scarcity of informationfound in the literature. We describe the insights we obtained from the annotationschema generation and validation process within our project, whose objectivesinclude the development of advanced sentiment analysis software of user reviews inthe tourism sector. We focus on the identification of the relevant entities and attributesin the domain, which we extract from a corpus of user reviews, and go on todescribe the schema creation and validation process. We begin by describing thecorpus annotation process and its further iterative refinement by means of severalinter-annotator agreement measurements, which we believe is key to a successfulannotation schema.
YR 2019
FD 2019-10-29
LK https://hdl.handle.net/10630/29610
UL https://hdl.handle.net/10630/29610
LA eng
NO Moreno-Ortiz, A., Salles-Bernal, S. & Orrequia-Barea, A. Design and validation of annotation schemas for aspect-based sentiment analysis in the tourism sector. Inf Technol Tourism 21, 535–557 (2019).
NO Esta obra es resultado de investigación del proyecto "Lingmotif2: Plataforma Universal de Análisis de Sentimiento" (FFI2016-78141-P), financiado con 48.800€ por el Ministerio de Economía, Industria y Competitividad
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 4 mar 2026