Textual Affect Sensing and Affective Communication

Textual Affect Sensing and Affective Communication

Mitsuru Ishizuka (School of Information Science and Technology, The University of Tokyo, Tokyo, Japan), Alena Neviarouskaya (Department of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Aichi, Japan) and Mostafa Al Masum Shaikh (Macquarie University, Macquarie Park, NSW, Australia)
DOI: 10.4018/jcini.2012100104
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Unlike sentiment analysis which detects positive, negative, or neutral sentences, textual affect sensing tries to detect more detailed affective or emotional states appearing in text, such as joy, sadness, anger, fear, disgust, surprise and much more. The authors describe here their following two approaches for textual affect sensing: The first one detects nine emotions using a set of rules implemented on the basis of a linguistic compositionality principle for textual affect interpretation. This process includes symbolic cue processing, detection and transformation of abbreviations, sentence parsing, and word/phrase/sentence-level analyses. The second one challenged to recognize 22 emotion types defined in the OCC (Ortony, Clore & Collins) emotion model, which is the most comprehensive emotion model and employs several cognitive variables. In this research, we have shown how these cognitive variables of the emotion model can be computed from linguistic components in text. These two approaches have exploited detailed level analyses of text in two different ways more than ever towards textual affect sensing. Applications towards affective communication are also outlined, including affective instant messaging, affective chat in 3D virtual world, affective haptic interaction, and online news classification relying on affect.
Article Preview

There are several approaches in textual affect sensing (Shanahan, 2006), namely: 1) affective keyword spotting (Strapparava, 2007), 2) commonsense approach (Liu, 2003), 3) rule-based approach (Boucouvalas, 2003; Chaumartin, 2007), and 4) machine learning approach (Kim, 2006; Alm, 2008).

The affective keyword spotting is simple and dependent basically on defined affect-bearing words; however, it is inaccurate in many cases because it disregards syntactic and semantic information of text. The commonsense approach strongly relies on collected real-world knowledge which is sometimes encoded in a graph form. The advantage of this approach is to take account of contextual information, if a similar situation exists in the knowledge base; however, it is hard or impossible to cover all the possible situations. The machine learning approach uses large annotated corpus and is popular especially for classifying sentiments, i.e., negative/positive opinions. It is difficult, however, in the affect sensing, to formulate diverse set of features; as a result, it mostly disregards modifiers, negation and condition constructions, syntactic relations and semantic dependencies in sentences. It can be said that the machine learning approach is semantically weak and less accurate for sentence-level analysis at present, though it is promising. The rule-based approach can take into account the contextual information and work on sentence level. The performance can be improved by adding rules and extending affective lexicon. The weakness of this approach is that rules always have exceptions. Nevertheless, this is the most practical at present. However, linguistic analyses have been weak in many rule-based approaches. Our two approaches are basically rule-based ones, but have incorporated elaborated functions into their linguistic analyses.

For example, a so-called polarity shift problem occurs in the following sentences:

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 11: 4 Issues (2017): 3 Released, 1 Forthcoming
Volume 10: 4 Issues (2016)
Volume 9: 4 Issues (2015)
Volume 8: 4 Issues (2014)
Volume 7: 4 Issues (2013)
Volume 6: 4 Issues (2012)
Volume 5: 4 Issues (2011)
Volume 4: 4 Issues (2010)
Volume 3: 4 Issues (2009)
Volume 2: 4 Issues (2008)
Volume 1: 4 Issues (2007)
View Complete Journal Contents Listing