Computer-Supported Narrative and Semantics Group

Understanding the meaning of documents, scripts and online content by computer-aided analysis of their structure and text

We apply advanced mathematical and computational methods (based on quantitative data analysis) to the analysis of narrative, to reveal its deep structure. The data analysis platform developed by the renowned geometric data analyst, Jean-Paul Benzécri, provides us with core methodological tools. These are augmented by the data analysis applications of Jean-Paul Benzécri's work by the acclaimed social scientist, Pierre Bourdieu. We compare these results with the theoretical and methodological approaches of different humanities disciplines to devise tools for the analysis of the structure of narrative in a new and fundamentally cross disciplinary approach.

New Additions, New Developments, News

Accompanying the paper by Fionn Murtagh and Giuseppe Iurato, "Visualization of Jacques Lacan's Registers of the Psychoanalytic Field, and Discovery of Metaphor and of Metonymy. Analytics Case Study of Edgar Allan Poe's "The Purloined Letter" ", here we have the Poe story set up, sentence by sentence, in this file: ThePurloinedLetterEdgarAllanPoe2.csv.
Accompanying this, most of the R software used for Lacan-related analytics of the Poe story is made available here: Rcode.txt, and, if required, clink_hcluswtd.r, for contiguity-constrained hierarchical clustering, where this is chronological contiguity.
International Satellite Symposium, WADP Congress 2017, On the Edge of Disciplines, invited speaker, 3 December 2016, Florence, Italy. WADP, 18th World Congree of the World Association for Dynamic Psychiatry. Magistral lecture, Fionn Murtagh, "Mapping the relationship between psychoanalytical paths and trajectories, and the contexts and practices within which they are to be found". Programme
Language and Mind Research Network.
Computational Psychoanalysis Research Group
International Bi-Logic Conference, "Emotional Thinking", London, 26-28 August 2016.
Recent submission: F. Murtagh, "The Geometry and Topology of Data and Information for Analytics of Processes and Behaviours: Building on Bourdieu and Addressing New Societal Challenges".
Symmetry, Proportion and Seriality: The Semantics of Mirroring and Repetition in Science and the Arts, Academia Europaea Conference, 26-28 May 2016, Freiburg Institute for Advanced Studies, Freiburg, Germany. Plenary address: F. Murtagh and R. Lauro-Grotto, "Geometric Data Analysis and Other Formal Approaches to Matte Blanco’s Bi-Logic: Symmetry and Asymmetry in Unconscious and Conscious Thought Processes".
Workshop, Data Mining in Human Activity Analysis (DMHAA), at IEEE ICDM2016, IEEE International Conference on Data Mining, 12 December 2016, Barcelona, Spain.
(Workshop, Data Mining in Human Activity Analysis, DMHAA). Special Issue of Signal Processing (Elsevier). Topic: Data Mining in Human Activity Analysis (DMHAA). Manuscript submission: 1 March 2017. Guest editors: Dr Xinmei Tian, Dr Weifeng Liu, Prof Fionn Murtagh, Dr Yijuan Lu. (Information available soon.)

Videos, Videocasts

Correspondence Analysis of the movie Casablanca, for displaying and tracking emotion: on YouTube.
TooManyCooks - see the description of "Advanced diagrams showing narrative structure and changes in style", on YouTube -- for students and teachers, for many others too, who are engaged in literacy or other areas of personal, educational, or social development. This is all to do with collaborative authoring, collective engagement and teamwork. Outcomes by Joe Reddington and his classes:
Videocast of presentation "Metric and Ultrametric Modelling of Semantics and Change for Decision Making in Dynamic and Interactive Environments", by Fionn Murtagh and Adam Ganz, Microsoft Research, Cambridge, 7 October 2011.

Software, Data

From a pair of hierarchical clusterings, determine the consensus hierarchy. Also determine the inherently, ultrametric-respecting triplets. Program CheckUMTriplets.r (here CheckUMTriplets.r.txt) as discussed in the paper, "Tracking subconscious underpinnings of cognition: an unsupervised pattern recognition approach to determining local ultrametricity".
Three dataset collections, as used in the paper, "Pattern Recognition in Narrative: Analysis of Narratives of Emotion" by F. Murtagh and A. Ganz.
Hierarchical reading visualization program, with sample books. HiRead v1.0.
1. Dialogue between Ilsa and Rick in key scenes in the Casablanca movie. CSV file..
2. From Chapters 9 to 12 of Flaubert's Madame Bovary, 22 successive text segments. Zip file containing 22 text files.
3. Twitter flows from New York Times, Le Monde, Guardian, Irish Times, Süddeutsche Zeitung. The original of each of these 1000-tweet flows, and the tweet texts alone, saved from R as .RData files. A readme file describes the setting up of these files.

Recent Events

Computational Psychoanalysis, group website.
Symmetry, Proportion and Seriality: The Semantics of Mirroring and Repetition in Science and the Arts Academia Europaea Conference, Freiburg, Germany, 26-28 May 2016. Plenary address: Fionn Murtagh and Rosapia Lauro-Grotto: "Matte Blanco's Bi-Logic: Symmetry and Asymmetry in Unconscious and Conscious Thought Processes"
ICCI*CC 2014 13th IEEE International Conference on Cognitive Informatics and Cognitive Computing, London South Bank University, London, UK. 18-20 August 2014. Including: Special Session on Computational Psychoanalysis.
Special Issue on Computational Psychoanalysis, International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) Volume 8, Issue 4, October - December 2014.
Foregoing includes: F. Murtagh, "Pattern recognition of subconscious underpinnings of cognition using ultrametric topological mapping of thinking and memory", International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 8(4), 1-16, 2014.
F. Murtagh, "Guest editorial preface", pp. iv-v.
Y. Wang (U. Calgary), E.T. Rolls (U. Warwick), N. Howard (MIT), V. Raskin (Purdue U.), W. Kinsner (U. Manitoba and TRLabs), F. Murtagh, V.C. Bhavsar (U. New Brunswick), S. Patel (London South Bank U.), D. Patel (London South Bank U.), S. Tsumoto (Shimane U.), and D.F. Shell (U. Nebraska-Lincoln), "Cognitive informatics: from information revolution to intelligence revolution", Intl. Jnl. of Software Science and Computation Intelligence, IJSSCI, 7(2), 50-69, 2015.

Recent Publications (See for preprints)

F. Murtagh, M. Pianosi, R. Bull, "Semantic Mapping of Discourse and Activity, Using Habermas's Theory of Communicative Action to Analyze Process", Quality and Quantity, in press.
F. Murtagh and M.J. Kurtz, "The Classification Society's Bibliography over four decades: History and content analysis", Journal of Classification, vol. 33, 2016, in press.
F. Murtagh, "Pattern recognition of subconscious underpinnings of cognition using ultrametric topological mapping of thinking and memory", International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 8(4), 2014. (Guest editor of Special Issue on Computational Psychoanalysis.) Link to journal site, with Guest Editorial Preface, foregoing article, and other articles in this special issue.
F. Murtagh, A. Ganz, "Pattern Recognition in Narrative: Tracking Emotional Expression in Context", Journal of Data Mining and Digital Humanities, in press, 2015.
Y. Wang (U. Calgary), E.T. Rolls (U. Warwick), N. Howard (MIT), V. Raskin (Purdue U.), W. Kinsner (U. Manitoba and TRLabs), F. Murtagh, V.C. Bhavsar (U. New Brunswick), S. Patel (London South Bank U.), D. Patel (London South Bank U.), S. Tsumoto (Shimane U.), and D.F. Shell (U. Nebraska-Lincoln), "Cognitive informatics: from information revolution to intelligence revolution", Intl. Jnl. of Software Science and Computation Intelligence, IJSSCI, forthcoming, 2015.
F. Murtagh and M. Farid, "The structure of argument: Semantic mapping of US Supreme Court cases", A. Gammerman, V. Vovk and H. Papadopoulos, Eds, Statistical Learning and Data Sciences, Springer Lecture Notes in Artificial Intelligence (LNAI) Volume 9047, 397-405, 2015.
F. Murtagh, "Mathematical representations of Matte Blanco's Bi-Logic, based on metric space and ultrametric or hierarchical topology: Towards practical application", Language and Psychoanalysis, Vol. 3, Issue 2, 2014. Article, dx.doi.org/10.7565, and this issue of the journal, and article in pdf.
F. Murtagh, "Pattern recognition in mental processes: Determining vestiges of the subconscious through ultrametric component analysis", in S. Patel, Y. Wang, W. Kinsner, D. Patel, G. Fariello and L.A. Zadeh (Eds.), Proceedings of the 2014 IEEE 13th International Conference on Cognitive Informatics and Cognitive Computing, Los Alamitos, CA: IEEE Computer Society Press, 2014, pp. 155-161.

Further Publications of Ours on Narrative Include:

J. Reddington, F. Murtagh and D. Cowie, "Computational properties of fiction writing and collaborative work", in Advances in Intelligent Data Analysis XII, Lecture Notes in Computer Science Volume 8207, 2013, pp 369-379.
F. Murtagh, "Thinking ultrametrically, thinking p-adically", in P. Pardalos, B. Goldengorin and F. Aleskerov, eds., Clusters, Orders, Trees: Methods and Applications, Springer, pp 249-272, 2014.
F. Murtagh, "Ultrametric model of mind, I: Review", p-Adic Numbers, Ultrametric Analysis and Applications, 4, 193-206, 2012.
F. Murtagh, "Ultrametric model of mind, II: Application to text content analysis", p-Adic Numbers, Ultrametric Analysis and Applications, 4, 207-221, 2012.
F. Murtagh, A. Ganz and J. Reddington, "Semantics from narrative: state of the art and future perspectives", in M. Gettler Summa, L. Bottou, B. Goldfarb, F. Murtagh, C. Pardoux and M. Touati, Eds., Statistical Learning and Data Science, Chapman & Hall/CRC Press, 2011, pp. 91-102.
F. Murtagh, A. Ganz and J. Reddington, "New methods of analysis and semantics in support of interactivity", Entertainment Computing, 2, 115-121, 2011. Preprint.
A. Ganz, "Leaping broken narration: Ballads, oral storytelling and the cinema", in L. Khatib, ed., Storytelling in World Cinema, Volume 1: Forms, Wallflower Press, 71-85, 2011.
F. Murtagh and A. Ganz, "Semantics from narrative", in S. Bolasco, I. Chiari and L. Giuliano, Eds., Statistical Analysis of Textual Data, Proceedings of 10th International Conference JADT Journées d'Analyse statistique des Données Textuelles, 9-11 June 2010, Sapienza University of Rome, Vol. 1, pp. 443-453, LED Edizioni Universitarie di Lettere Economia Diritto, Milan, 2010.
F. Murtagh and A. Ganz, "Segmentation and nodal points in narrative: study of multiple variations of a ballad", preprint, 2010.
A. Ganz, "Let the audience add 2 + 2 and they'll love you for ever". The screenplay as a self-teaching system. In Analysing the Screenplay, edited by Jill Nelmes, Routledge, pp. 127-141, 2010.
F. Murtagh and A. Ganz, La sémantique d'un récit : état de l'art et perspectives, La Revue MODULAD, 42, 36-44, 2010.
A. Ganz, Time, space and movement: Screenplay as oral narrative, Journal of Screenwriting, 1 (2), 2010.
F. Murtagh, A. Ganz, S. McKie, J. Mothe and K. Englmeier, Tag clouds for displaying semantics: the case of filmscripts, Information Visualization, 9, 253-262, 2010.
F. Murtagh, A. Ganz and S. McKie, The structure of narrative: the case of film scripts, Pattern Recognition, 42, 302-312, 2009.
A. Ganz and L. Khatib, guest editors, Reconstruction: Studies in Contemporary Culture Journal, special issue on Visualization and Narrative, Vol. 8, No. 3, 2008.
F. Murtagh, The Correspondence Analysis platform for uncovering deep structure in data and information, Sixth Annual Boole Lecture in Informatics. The Computer Journal, 53 (3), 304-315, 2010.
A. Ganz and L. Khatib, Digital cinema: The transformation of film practice and aesthetics, New Cinemas: Journal of Contemporary Film, volume 4, issue 1, pp. 21-36, 2006.
A. Ganz, Cause Trouble! Inspire Change! Do it First? - Writing series drama for Channel 4, Journal of Media Practice, volume 8, number 3, 273-288, 2007. A version of this paper was given at the BFI Conference commemorating the 25th Anniversary of Channel 4.
F. Murtagh, Correspondence Analysis and Data Coding with R and Java, Chapman and Hall/CRC Press, 2005. Chapter 5, Text Analysis. For software see www.correspondances.info.

Awards

"Project TooManyCooks: Applying Software Design Principles to Fiction Writing", including a considerable number of course participant testimonials, by D. Cowie (Dept. of English), J. Reddington and F. Murtagh (both Dept. of Computer Science) won in May 2010 a prestigious RHUL College Team Teaching Prize, the aim of which is "to acknowledge and reward either a single initiative or a range of initiatives which have had a beneficial impact on student learning at Royal Holloway". Photo!

Events - Workshops, Conference Sessions

Plenary presentation, Fionn Murtagh, JOCLAD 2012, XIX Jornadas de Classificação e Análise de Dados, Tomar, Portugal, 28-31 March 2012.
Videocast of presentation at Microsoft Research Cambridge, Fionn Murtagh and Adam Ganz, 7 October 2011.
Presentation at ICC 2011, International Classification Conference, University of St Andrews, 11-15 July 2011.
Keynote at RCOMM 2011, Rapid-Miner Community Meeting and Conference, Institute of Technology Blanchardstown, Dublin, 7-10 June 2011.
J. Reddington, "Software Engineering the Novel", seminar, Royal Holloway, University of London, 9 March 2011.
F. Murtagh, J. Reddington and A. Ganz, "Semantics of narrative in collective, distributed problem-solving environments based on correspondence analysis and hierarchical clustering", CARME 2011, International Conference on Correspondence Analysis and Related Methods, Rennes, 8-11 February 2011.
F. Murtagh, J. Reddington and A. Ganz, "Correspondence analysis and hierarchical clustering in semantic and stylistic analysis of text, with application to film, TV, and other domains", British Classification Society meeting, UCL, 24 September 2010.
F. Murtagh, A. Ganz and J. Reddington, "Narrative Synthesis in Interactive Settings", SID2010, 9th International Workshop on Social Intelligence Design, Royal Holloway, University of London, 13-16 September 2010.
F. Murtagh and A. Ganz, "New methods of analysis of narrative and semantics in support of interactivity", keynote presentation, The 1st International Workshop on Serious Games Development and Applications, University of Derby, Kedleston Road, Derby, 8 July 2010.
F. Murtagh, "Semantics from narrative", keynote presentation, JADT 2010, 10th International Conference on Statistical Analysis of Textual Data, Rome, 9-11 June 2010.
A. Ganz and F. Murtagh, "From data mining in digital humanities to new methods of analysis of narrative and semantics", presentation at The Computational Turn, workshop, Swansea University, 9 March 2010.
Film, Visualization, Narrative, a workshop run by Adam Ganz, Royal Holloway, University of London, 17 Nov. 2006, supported by the AHRC ICT Methods Network and LCACE (London Centre for Arts and Cultural Enterprise).

Our Work In The News

Interview on TV screenplay structure, with Adam Ganz, La Repubblica, 23 Jan. 2010.
Guest participation on the Colin McEnroe Show on WNPR - Connecticut Public Radio, 20 January 2010.
The secret of ratings success. Why are academics applying algorithms to episodes of the TV drama CSI Las Vegas?, The Guardian, 1 December 2009.
L'algoritmo del serial perfetto, C'è une formula matematica alla base del successo di "Lost" e "Csi", La Stampa, 15 December 2009.
La scenegggiatura perfetta? (Corriere Della Sera, 1 December 2009).
TV Listings 03/12/09, Academics probe TV ratings success, p. 6, Gulf Times, Qatar, 3 December 2009.
Such den Blockbuster, such!, Stern, 11 June 2008.
Wie man Blockbuster vorhersagt. Software soll erfolgreiche Filme anhand des Drehbuchs identifizieren, Bild der Wissenschaft, 6 June 2008.
Software dla scenarzystów, Focus.pl, 13 June 2008.
Here's looking at you, kid. Software promises to identify blockbuster scripts, Nature, vol. 453, p. 708, 4 June 2008.

People (and Lots of Other Things)

Adam Ganz, Department of Media Arts.
Fionn Murtagh, Professor of Data Science.
Stewart McKie: Scriptgeist. Screenpad.
Joe Reddington. Time, space and movement: Screenplay as oral narrative
Joe Reddington's Project Too Many Cooks showing some examples of how a display of the internal, semantically-realted, structure of the book being read can help in reading.
By Joe Reddington - Tim Cooks, Deception of Success, e-Book published as a Kindle book on Amazon, 2011. Written collectively by a group of schoolchildren, average age 12, in less than a week. Amazing work! See our paper in Entertainment Computing, vol. 2, pp. 115-121, 2011, for some discussion. Kindle boooks.
Douglas Cowie, Department of English.

Where We Participate Too

i-Teams, Commercialising Creativity, project Analysing screenplays, books, and online discussions, at i-Teams Cambridge, 2011.
Center for Research in Entertainment and Learning (CREL), hosted by the UCSD, University of California San Diego, Division of the California Institute for Telecommunications and Information Technology. Press release on 24 Feb. 2010, New UCSD Center to Study the Meaning Behind Interactive Media in Learning and Entertainment".
CLRC, Computer Learning Research Centre, RHUL.
iCOM, Centre for Research in Information Computing and Communication, RHUL.
ICT4D, Information and Communication Technologies for Development, RHUL.
Finally, some notes on Crowdsourcing and Citizen Science.

Last update: 2015 August 30. Contact: f m u r t a g h _a t_ a c m _d o t_ o r g