Actor-Role Analysis: Ideology, Point of View, and the News

paper
Authorship
  1. 1. Warren Sack

    Media Laboratory - Massachusetts Institute of Technology

Work text
This plain text was ingested for the purpose of full-text search, not to preserve original formatting or readability. For the most complete copy, refer to the original conference program.

Abstract: A representation of ideological point of
view is articulated and a method for detecting the
point(s) of view expressed in a news story is
described. A version of the method, actor-role
analysis, is encoded in a computer program, SpinDoctor, which can automatically detect the
point(s) of view represented in some news stories.
Results obtained by testing SpinDoctor on a corpus of news stories are reported and the actor-role
analysis method is compared to other methods of
ideological analysis in the fields of linguistics,
literary theory, and science studies.
This paper describes a computational technique
for text analysis, specifically, for the analysis of
news texts. It improves upon existing work in
artificial intelligence (AI) natural language processing (NLP) and challenges existing models of
ideology (e.g., Fredric Jameson’s use of Greimasian semiotics to represent ideological limits.) Previous work in AI news story understanding has
largely been used to build tools which can summarize stories and categorize them according to the
events they describe (e.g., the technologies developed for the Message Understanding Conferences (MUC)). The Message Understanding Conferences are sponsored by the Defense Advanced
Research Projects Agency (DARPA) to test leading artificial intelligence natural language processing programs against one another. In this paper some of the MUC3 (1991) test corpus will be
examined.
These sorts of technologies are built around the
assumptions that (1) events reported as facts in
news stories should be “understood” as facts; (2)
the style of a story, i.e., the way in which the story
is told, is not of interest; and, (3) the source of a
story should not influence its analysis. These assumptions are obviously unrealistic. By making
these simplifying assumptions most existing story
understanding systems function as gullible “readers.” [There are some early exceptions (e.g.,
Abelson and Carroll, 1966) and this neglect has
not been complete in closely related areas (in
dialog and argument understanding, e.g., Allen
and Perrault, 1980; Birnbaum, Flowers and
McGuire, 1980; Alvarado, 1990; intelligent tutoring systems, e.g., Farrell and Bloch, 1988; and, in
the field of language generation, e.g., Hovy,
1988).] Everyone knows that one should not believe everything in the news. To build a less gullible news story analyzer it will be necessary to
encode in it a means to recognize point of view.
By point of view I mean ideological point of view
as opposed to, for example, psychological point of
view. Ideological point of view characterizes the
political slant of an entire story while psychological point of view (e.g., as it is used by Wiebe,
1994) characterizes the source of a given sentence
or statement contained within a story.
This paper describes SpinDoctor, a computer program designed to detect ideological point of view
in news stories. To detect point of view, SpinDoctor implements a critical reading strategy called
actor-role analysis (Sack, 1994b). Actor-role analysis can be compared to a variety of semiotic-based methods for analyzing conflicts and ideological difference (e.g., Bruno Latour’s actor-network
analyses of science texts; Latour, 1987). Actorrole analysis was developed around the following
observation: one means of detecting point of view
is to examine how certain people, who appear
again and again in the news (i.e., news actors), are
described or portrayed (i.e., are assigned roles).
Thus, for example, if one is given a news story
which mentions Oliver North – (in)famous for his
role in the Iran-Contra affair and recent senatorial
campaign – and the story assigns North the role of
patriot (via the use of certain adjectives and verbs),
one can be quite certain that the point of view
expressed in the story is significantly to the right
(in the spectrum of US politics) than that expressed by another news story which assigns North the
role of villain or criminal.
Two aspects of actor-role analysis, as it is implemented in the SpinDoctor system, might be of
especial interest to researchers concerned with
computational textual analysis:
(1) A representation for ideological point of view:
Although practically all, contemporary, AI systems for NLP are capable of finding actors and
roles in texts to fill in scripts, frames, or templates
(e.g., Jacobs and Rau, 1993), none of these systems assign any political significance to the pairing of certain actors with certain roles (e.g., North
as patriot versus North as criminal). By contrast,
we maintain that sets of actor-role pairs are an
interesting and implementable representation for
differing ideological points of view. The proposed
actor-role representation of ideological point of
view accords with some recent work by Lakoff
(1991) and generalizes and improves upon previous AI work on representation of ideology (e.g.,
Abelson and Carroll, 1966; Carbonell, 1978).
(2) An algorithm for anaphoric resolution: Actorrole analysis incorporates a new anaphoric resolution algorithm. It is shown how careful attention
to actor-role pairings assists in the resolution of
anaphoric reference. By noting, for example, that
an instance of the pronoun “he” is cast in the role
of victim and that, earlier in the same story, “Lieut.
Rodriguez” is also cast in the role of victim, SpinDoctor postulates the resolution of the instance of
the pronoun “he” to the proper name “Lieut. Rodriguez.”
This paper describes the data structures and processes implemented in the SpinDoctor system and
examines how the implemented actor-role analysis method compares to related work in ideological analysis explored in literary theory (e.g.,
Jameson, 1987); linguistics (e.g., Lakoff, 1991);
and science studies (e.g., Latour, 1987).
References
Abelson, R.P. and Carroll, J.D. (1965) “Computer
Simulation of Individual Belief Systems”,
American Behavior Scientist, 8, 24-30.
Carbonell, J. (1979) Subjective Understanding:
Computer Models of Belief Systems. Ph.D.
Thesis. New Haven, CT: Yale University
Computer Science Department, Technical Report 150.
Jameson, F. (1987) Foreword, in Greimas, A.J.,
On Meaning: Selected Writings in Semiotic
Theory (trans. P.J. Perron & F.H. Collins)
(Minneapolis: University of Minnesota Press).
Jacobs, P. and Rau, L. (1993) Innovations in Text
Interpretation, Artificial Intelligence, 63(1-2),
143-192.
Lakoff, G. (1991) “Metaphor and War: The Metaphor System Used to Justify the War in the
Gulf”, Journal of Urban and Cultural Studies,
Volume 2, Number 1, pp. 59-72.
Latour, B. (1987) Science in Action: How to follow scientists and engineers through society
(Cambridge, MA: Harvard University Press).
Latour, B. Mauguin, P. & Teil, G. (1992) A Note
on Socio-Technical Graphs, Social Studies of
Science, Vol. 22, 33-57.
MUC-3 (1991) Proceedings of the Third Message
Understanding Conference, San Mateo, CA:
Morgan Kaufmann Publishers, Inc.
Sack, W. (1994) Actor-Role Analysis: Ideology,
Point of View and the News (Technical Report
94-005) Cambridge, MA: MIT Media Laboratory, Learning and Common Sense Section.
Wiebe, J. (1994) Tracking Point of View in Narrative, Journal of Computational Linguistics,
June 1994.

If this content appears in violation of your intellectual property rights, or you see errors or omissions, please reach out to Scott B. Weingart to discuss removing or amending the materials.

Conference Info

In review

ACH/ALLC / ACH/ICCH / ALLC/EADH - 1996

Hosted at University of Bergen

Bergen, Norway

June 25, 1996 - June 29, 1996

147 works by 190 authors indexed

Scott Weingart has print abstract book that needs to be scanned; certain abstracts also available on dh-abstracts github page. (https://github.com/ADHO/dh-abstracts/tree/master/data)

Conference website: https://web.archive.org/web/19990224202037/www.hd.uib.no/allc-ach96.html

Series: ACH/ICCH (16), ALLC/EADH (23), ACH/ALLC (8)

Organizers: ACH, ALLC