webLyzard Publications

An Evaluation Framework and Adaptive Architecture for Automated Sentiment Detection

Gindl, Stefan and Liegl, Johannes and Scharl, Arno and Weichselbraun, Albert (2009) An Evaluation Framework and Adaptive Architecture for Automated Sentiment Detection. In: Networked Knowledge - Networked Media: Integrating Knowledge Management, New Media Technologies and Semantic Systems. Studies in Computational Intelligence, 221 . Springer, Heidelberg, pp. 217-234.

PDF (An Evaluation Framework and Adaptive Architecture for Automated Sentiment Detection) - Accepted Version

Official URL: http://www.springerlink.com/content/ul481174018124...


Analysts are often interested in how sentiment towards an organization, a product or a particular technology changes over time. Popular methods that process unstructured textual material to automatically detect sentiment based on tagged dictionaries are not capable of fulfilling this task, even when coupled with part-of-speech tagging, a standard component of most text processing toolkits that distinguishes grammatical categories such as article, noun, verb, and adverb. Small corpus size, ambiguity and subtle incremental change of tonal expressions between different versions of a document complicate sentiment detection. Parsing grammatical structures, by contrast, outperforms dictionary-based approaches in terms of reliability, but usually suffers from poor scalability due to its computational complexity. This work provides an overview of different dictionary- and machine-learning-based sentiment detection methods and evaluates them on several Web corpora. After identifying the shortcomings of these methods, the paper proposes an approach based on automatically building Tagged Linguistic Unit (TLU) databases to overcome the restrictions of dictionaries with a limited set of tagged tokens.

Item Type:Book Section
Uncontrolled Keywords:sentiment detection, tagged linguistic unit, opinion mining, spreading activation network
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:Faculty of Engineering, Science and Mathematics > School of Electronics and Computer Science
ID Code:41
Deposited By: Dr Albert Weichselbraun
Deposited On:16 Apr 2012 06:47
Last Modified:16 Apr 2012 06:47

Repository Staff Only: item control page