Using the concept of transforming sequences to automatically extract and classify bursts

Mahlow, Cerstin; Ulasik, Malgorzata Anna

Publication type:	Conference other
Type of review:	Peer review (abstract)
Title:	Using the concept of transforming sequences to automatically extract and classify bursts
Authors:	Mahlow, Cerstin Ulasik, Malgorzata Anna
et. al:	No
Conference details:	Writing Research Across Borders, Trondheim, Norway (online), 18-23 February 2023
Issue Date:	Feb-2023
Language:	English
Subjects:	Transforming sequence; Burst; Writing research; Writing process; THETool
Subject (DDC):	808: Rhetoric and writing
Abstract:	The overall goal of our research is to understand the production of linguistic units to better support writers during revision and to help them to effectively use structures considered essential for academic writing. With THETool (Text History Extraction Tool) we are able to automatically explore writing on a structural level (syntax in the broadest sense) and gain relevant insights (Mahlow et al. 2022). THETool parses keystroke-logging data and creates text and sentence histories for a particular writing session. Sentence histories cover all events relevant for a sentence. In a particular sentence history, we can follow what the writer did, even when they came back to a sentence several times. This history contains all different versions of this sentence during the writing session. A version of a particular sentence is created every time a specific text-produced-so-far (TPSF) can be detected and saved, which depends on the writer switching modes of producing (including deleting) texts. We call the difference between two consecutive versions the transforming sequence (TS), which we consider an instantiation of a burst. A TS can either be a deletion, an insertion, or an extension to the current sentence. Several attempts have been made to explore bursts and propose extensive classifications. Baaijen et al (2012) and Galbraith and Baaijen (2019) work on modeling bursts (Kaufer et al, 1986), taking into account type of bursts as either production or revision bursts. They rely on manual annotation of keystroke-logging data and, to the best of our knowledge, no replication (maybe even for writing in other languages) or extension of their approach has been done so far as the manual annotation process is difficult. With THETool we aim to test their classification scheme automatically on large collections of writing sessions. For revision bursts, connections to taxonomies of revision activities could be drawn, but again this is very laborious and has not been done automatically before. However, with THETool we will be able to explicitly address and build on previous work: Bridwell (1980) and Sommers (1980) focus on observable revisions at the surface of the text and distinguish syntactic structures involved. Faigley and Witte (1981) and later Fitzgerald (1987) aim at categorizing changes in meaning of the text on the basis of observable structural changes. Allal and Chanquoy (2004) and Lindgren (2005) introduce the notions of pretextual and precontextual revisions, i.e., mental changes before the author transcribes them—but as such revisions are not directly observable through the process and product data, we do not consider them here. We hope, however, to be able to find some evidence to construct dedicated experiments to further explore these aspects based on specific classes of bursts. We propose a taxonomy of bursts based on the surface (i.e., the language visible on screen or paper) and the syntactic structure of a transforming sequence. Additional features address (1) the actions and production mode (deletion, insertion, extension) before and after a specific revision, (2) the distance between a previous point of inscription in the text and the current one, (3) the distance between the current point of inscription and the current position in the text, (4) the grammatical status of the sentence before and after the revision action, and (5) the location of the previous action, the current point of inscription, and the following action.
Further description:	References: - Allal L, Chanquoy L (2004) Introduction: Revision Revisited. In: Allal L, Chanquoy L, Largy P (eds) Revision. Cognitive and instructional processes, Studies in Writing, vol 13, Kluwer, Boston, Dordrecht, London, pp 1–7. - Baaijen VM, Galbraith D, de Glopper K (2012) Keystroke Analysis. Written Communication 29(3):246–277, DOI 10.1177/0741088312451108. - Bridwell LS (1980) Revising Strategies in Twelfth Grade Students’ Transactional Writing. Research in the Teaching of English 14(3):197–222, URL http://www.eric.ed.gov/ERICWebPortal/detail accno=EJ236505 - Faigley L, Witte S (1981) Analyzing Revision. College Composition and Communication 32(4):400–414, DOI 10.2307/356602. - Fitzgerald J (1987) Research on Revision in Writing. Review of Educational Research 57(4):481–506, DOI 10.2307/1170433. - Galbraith D, Baaijen VM (2019) Aligning keystrokes with cognitive processes in writing. In: Lindgren E, Sullivan K (eds) Observing writing, Brill, Leiden, The Netherlands, pp 306–325. - Kaufer DS, Hayes JR, Flower L (1986) Composing written sentences. Research in the Teaching of English 20(2):121–140, URL http://www.jstor.org/stable/40171073. - Lindgren E (2005) Writing and revising: Didactic and Methodological Implications of Keystroke Logging. PhD thesis, Umeå Universitet, URL http://www.divaportal.org/umu/abstract.xsql?dbid=534. - Mahlow C, Ulasik MA, Tuggener D (2022) Extraction of transforming sequences and sentence histories from writing process data: a first step towards linguistic modeling of writing. Reading and Writing. DOI 10.1007/s11145–021–10234–6. - Sommers N (1980) Revision Strategies of Student Writers and Experienced Adult Writers. College Composition and Communication 31(4):378–388, DOI 10.2307/356588.
URI:	https://digitalcollection.zhaw.ch/handle/11475/27154
Fulltext version:	Accepted version
License (according to publishing contract):	Not specified
Departement:	Applied Linguistics
Organisational Unit:	Institute of Language Competence (ILC)
Appears in collections:	Publikationen Angewandte Linguistik

Files in This Item:

There are no files associated with this item.

Show full item record

Mahlow, C., & Ulasik, M. A. (2023, February). Using the concept of transforming sequences to automatically extract and classify bursts. Writing Research across Borders, Trondheim, Norway (Online), 18-23 February 2023.

Mahlow, C. and Ulasik, M.A. (2023) ‘Using the concept of transforming sequences to automatically extract and classify bursts’, in Writing Research Across Borders, Trondheim, Norway (online), 18-23 February 2023.

C. Mahlow and M. A. Ulasik, “Using the concept of transforming sequences to automatically extract and classify bursts,” in Writing Research Across Borders, Trondheim, Norway (online), 18-23 February 2023, Feb. 2023.

MAHLOW, Cerstin und Malgorzata Anna ULASIK, 2023. Using the concept of transforming sequences to automatically extract and classify bursts. In: Writing Research Across Borders, Trondheim, Norway (online), 18-23 February 2023. Conference presentation. Februar 2023

Mahlow, Cerstin, and Malgorzata Anna Ulasik. 2023. “Using the Concept of Transforming Sequences to Automatically Extract and Classify Bursts.” Conference presentation. In Writing Research across Borders, Trondheim, Norway (Online), 18-23 February 2023.

Mahlow, Cerstin, and Malgorzata Anna Ulasik. “Using the Concept of Transforming Sequences to Automatically Extract and Classify Bursts.” Writing Research across Borders, Trondheim, Norway (Online), 18-23 February 2023, 2023.