Modeling emotional tone in stories using tension levels and categorical states

Anderson, C. W.; McMaster, G. E.

doi:10.1007/bf02393459

Cited by 16 publications

(6 citation statements)

References 13 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some TDA programs attempt to compensate for this by building in flexibility to address implicit or tacit aspects of the data. For example, Anderson and McMaster's (1986) psychological semantic analysis computer program attempts to account for context by displaying the words with more than one conceptual meaning in short sentences so that the user can decide how the words should be scored. Unfo~unately, as more human inte~ention is needed, some of the efficiencies afforded by computer-facilitated qu~itative data analysis are diminished.…”

Section: Discussionmentioning

confidence: 99%

“…For example, using Heise"s (1965) list of 1000 most common English words, Anderson and McMaster (1982) described patterns of change in the affective tone of various types of juvenile and adult literature. They conehzded that ~x~rni~~~ affective connotation in textual materials can add ~~o~at~on blond that prodded by the literal .rne~~~g uf the text.…”

Section: Tande ~~~~~U~~~~ U~~~~e~~ In ~~~~~Ementioning

confidence: 99%

See 1 more Smart Citation

Measuring Emotion in Open-ended Survey Responses: An Application of Textual Data Analysis

Harris¹

1995

Journal of Management

View full text Add to dashboard Cite

The present study illustrates the use of a qualitative research technique, textual data analysis, in assessing the emotional content of open-ended survey responses. The Dictionary of Affect in Language (DAL), one of many acceptable routes to the measurement of emotion, provided the basis for scoring open-ended responses collected in a study of the organizational transformation efforts of a Fortune 100 firm based in the midwestern United States. Managers and corporate executives were surveyed with an in-depth questionnaire that included quantitative measures of several work-related perceptions and attitudes as well as open-ended questions regarding two major events that occurred during the transformation. Dimension scores produced from the DAL and direct ratings of open-ended responses correlated with the quantitative measures in expected and consistent ways. The use of textual data analytic approaches is discussed, and advantages and disadvantages of such approaches are broadly addressed.Organizational researchers have taken advantage of the speed with which computers can process numerical data for quite some time. In contrast, analyses involving textual data have more often been considered as a time-consuming, labor-intensive undertaking less suitable for computer processing. The complexity and volume that characterize textual data have oft been recognized as presenting special challenges to research analysts. Recently however, the emergence of specialized text processing software and more powerful computers has renewed interest in research possibilities associated with the examination and interpretation of textual data (Danziger

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Tande ~~~~~U~~~~ U~~~~e~~ In ~~~~~Ementioning

confidence: 99%

Measuring Emotion in Open-ended Survey Responses: An Application of Textual Data Analysis

Harris¹

1995

Journal of Management

View full text Add to dashboard Cite

show abstract

“…Heise (1965) obtained E and A values empirically, presenting only the 1,000 most frequent English words to 342 U.S. Navy personnel for rating. When Anderson and McMaster (1986) assigned these values to the words in their texts, they report that the number of Heise-dictionary words present in the texts ( " hits") ranged between only 1 and 31 for their 100-word blocks. This constraint on the number of possible hits clearly limits the accuracy of the Heise dictionary in representing emotional patterns, especially for short texts.…”

Section: Methodsmentioning

confidence: 99%

“…Heise (1965) was careful to present words for rating in neutral contexts, but this does not address the problem facing researchers seeking to assign accurate values to words in emotional contexts. For example, Anderson and McMaster (1986) assigned to the word "wild" in "wild geese" (a species name) the same value that Heise had assigned to it using the criterion phrase "it was wild talk" (representing the then most frequent usage of "wild" in American English). In Heise's context, "wild" is an adjective selected to convey a quality akin to "untamed," rather than an obligatory component of a species name as it is in "wild geese."…”

Section: Methodsmentioning

confidence: 99%

“…Bestgen (1994) concluded that his results validate a dictionary -based technique of measuring the emotional content of texts, provided that the dictionary is "exhaustive as well as adapted to the texts to be analyzed" (p. 30). Bestgen's provisos "exhaustive" and "adapted" recall the problems of low hit rate and decontextualization we saw in Anderson and McMaster's (1986) use of the Heise dictionary.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Emotion in Language and Speech: Methodological Issues in Naturalistic Approaches

2000

View full text Add to dashboard Cite

Researchers currently seek to improve validity in speech and language studies by adopting naturalistic procedures In emotion-display research, validity is threatened by standard experimental controls which diminish the naturalism of stimuli and response ranges. We report two experiments comparing the adequacy of naturalistic with standard procedures. Experiment 1 had 158 judges code 89 samples of naturally-occurring emotional speech with free-choice emotion labels, and later with labels from a standard set. When free-choice labels were similar across judges, they were consistent with standard labels, but showed a range of intensity and contextual relevance. We recommend that future studies include wider options for judges when coding emotions. Experiment 2 compared valency ratings of words when presented in, or out of, context. Standard procedures score lexical valencies using affective dictionaries, disregarding natural contexts. Experiment 2 compared 23 judges' valency ratings of words presented individually, and later in their original context. Between 30% and 44% of words were rated differently in context (depending on the statistical significance level adopted). We concluded from Experiment 2 that, where small corpora adequately model a domain, the improved accuracy of valency rating achieved by presenting words in their natural context justifies the extra procedures required.

show abstract

Traditional and emotional stylometric analysis of the songs of Beatles Paul McCartney and John Lennon

Whissell

1996

Comput Hum

View full text Add to dashboard Cite

Traditional stylometric measures such as word usage, word length, and word repetition were paired with six new measures that described word emotionality in terms of a word's pleasantness, its activation level, and the combination of these factors. All measurements were applied to the songs composed by Beatles Paul McCartney and John Lennon between 1962 and 1970. Stylistic and emotional differences between composers and across years were found to be in agreement with observations made by critics and analysts of Beatles' songs, suggesting that emotional stylometry is a valid instrument for the analysis of text. Lennon was the less pleasant and the sadder lyricist, and the Lennon-McCartney lyrics became less pleasant, less active, and less cheerful over time. Several other differences were observed and reported. A technique for summary emotional description (the emotion clock) was also introduced.

show abstract

Modeling emotional tone in stories using tension levels and categorical states

Cited by 16 publications

References 13 publications

Measuring Emotion in Open-ended Survey Responses: An Application of Textual Data Analysis

Measuring Emotion in Open-ended Survey Responses: An Application of Textual Data Analysis

Emotion in Language and Speech: Methodological Issues in Naturalistic Approaches

Traditional and emotional stylometric analysis of the songs of Beatles Paul McCartney and John Lennon

Contact Info

Product

Resources

About