Comparison of Text Analysis Programs for Identification of Emotional Expression

<p>Studies have show that written emotional expression assists in the recovery and alleviates the pain associated with traumatic experiences, cancer diagnoses, and chronic illnesses. Written interventions have been developed to utilize this emotional coping approach. Unfortunately, evaluation of participants and patients written text is time consuming and subjective to the coder. Researchers have developed computational text analysis programs in an attempt to find an alternative to human coders for text analysis. The current study will utilize data from previous research performed by Owen et al., (2005) entitled <em>Randomized Pilot of a Self-Guided Internet Coping Group for Women With Early Stage Breast Cancer, </em>as well as from research performed by Bantum and Owen, (2009) entitled <em>Evaluating the Validity of Computerized Content Analysis Programs for Identification of Emotional Expression in Cancer Narratives. </em>This present study will evaluate the previously collected data to examine the validity between the previously validated Linguistic Inquiry and Word Count 2001 and the Linguistic Inquiry and Word Count 2007, which has been edited based on the downfalls of the previous model. Results indicate that LIWC 2001 and LIWC 2007 have a high validity in their ability to identify emotional expression; however, LIWC 2001 is superior in its precision of emotional identification. When comparing the results of LIWC 2001 and LIWC 2007 with human coders, LIWC 2001 most accurately reflects the human coders in emotional identification.</p>

Name thesis:degree_name

Doctor of Philosophy (PhD)

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Psychology

Year

2015

Author dc:creator

• McDonnell, Michelle

Contributors dc:contributor

• Owen, Jason E.
• Boyd, Kendal
• Vermeersch, David A.

• Clinical Psychology
• Psychology
• Social and Behavioral Sciences
• Emotions -- Psychological aspects; Emotions -- Measurement; Psycholinguistics; Emotive (Linguistics); Psychological Tests
• Emotional Expression; Computational text analysis; Linguistic Inquiry and Word Count; Emotional Identification;

Statement dc:rights

• This title appears here courtesy of the author, who has granted Loma Linda University a limited, non-exclusive right to make this publication available to the public. The author retains all other copyrights.

Language dc:language

English

Repository record dc:identifier

https://scholarsrepository.llu.edu/etd/308

OAI identifier oai:identifier

oai:scholarsrepository.llu.edu:etd-1310