LINGUIST List 19.2434
|
Tue Aug 05 2008
Diss: Comp Ling/Semantics: Alm: 'Affect in Text and Speech'
Editor for this issue: Evelyn Richter
<evelyn linguistlist.org>
|
To post to LINGUIST, use our convenient web form at
http://linguistlist.org/LL/posttolinguist.html.
|
Directory
1. Ebba Cecilia
Alm,
Affect in Text and Speech
Message 1: Affect in Text and Speech
|
Date: 05-Aug-2008
From: Ebba Cecilia Alm <eoa5cornell.edu>
Subject: Affect in Text and Speech
 E-mail this message to a friend
Institution: University of Illinois at Urbana-Champaign
Program: Department of Linguistics
Dissertation Status: Completed
Degree Date: 2008
Author: Cecilia Ovesdotter Alm
Dissertation Title: Affect in Text and Speech
Dissertation URL: http://lrc.cornell.edu/swedish/dataset/affectdata/index.html
Linguistic Field(s):
Computational Linguistics
Semantics
Dissertation Director:
Richard W. Sproat
Dissertation Abstract:
As technology and human-computer interaction advances, there is an
increased interest in affective computing. One of the current challenges in
computational speech and text processing is addressing affective and
expressive meaning, an area that has received fairly sparse attention in
linguistics. Linguistic investigation in this area is motivated both by the
need for scientific study of subjective language phenomena, and by useful
applications such as expressive text-to-speech synthesis. The study makes
contributions to the study of affect and language, by describing a novel
data resource, outlining models and challenges for exploring affect in
language, applying computational methods toward this problem with included
empirical results, and suggesting paths for further research.
After the introduction, followed by a survey of several areas of related
work in Chapter 2, Chapter 3 presents a newly developed sentence-annotated
corpus resource divided into three parts for large-scale exploration of
affect in texts (specifically tales). Besides covering annotation and data
set description, the chapter includes a hierarchical affect model and a
qualitative-interpretive examination suggesting characteristics of a subset
of the data marked by high agreement in affective label assignments.
Chapter 4 is devoted to experimental work on automatic affect prediction in
text. Different computational methods are explored based on the labeled
data set and affect hierarchy outlined in the previous chapter, with an
emphasis on supervised machine learning whose results seem particularly
interesting when including true affect history in the feature set.
Moreover, besides contrasting classification accuracy of methods in
isolation, methods' predictions are combined with weighting approaches into
a joint prediction. In addition, classification with the high agreement
data is specifically explored, and the impact of access to knowledge about
previous affect history is contrasted empirically. Chapter 5 moves on to
discuss emotion in speech. It applies interactive evolutionary computation
to evolve fundamental parameters of emotional prosody in perceptual
experiments with human listeners, indicating both emotion-specific trends
and types of variations, and implications at the local word-level. Chapter
6 provides suggestions for continued work in related and novel areas. A
concluding chapter summarizes the dissertation and its contributions.
Read more issues|LINGUIST home page|Top of issue
|
|
Please report any bad links or misclassified data
LINGUIST Homepage | Read
LINGUIST | Contact us
While the LINGUIST List makes every effort to ensure the linguistic relevance of sites listed
on its pages, it cannot vouch for their contents.
|
|
