Conference Agenda

Keynote 3, Long Papers
Thursday, 19/Mar/2020:
11:00am - 12:50pm

Session Chair: Christian-Emil Ore
Location: Ziedonis Hall
Ground floor

Keynote speaker (50min)

Digital Emotions: Hybrid Structure of Emotional Impacts

Jurģis Šķilters

Laboratory for Perceptual and Cognitive Systems, University of Latvia

After a brief overview of the current state of art in the field of research on emotions, I will explore the way emotions impact users in interface systems in virtue of affective reactions to colors and shapes. I will provide evidence from the work conducted in my lab. Further, I will discuss effects of emotional reactions (e.g., emotional contagion) in large-scale digital social networks and will argue for a more universal approach to emotional patterns in digital environments.

Long Paper (20+10min)

Implications of Multifractal Theory for Fictional Narratives - A Dynamic Perspective on Sentiment-Based Story Arcs Exemplified by Ishiguro's Never Let Me Go

Kristoffer Nielbo1, Qiyue Hu2, Bin Liu5, Mads Rosendahl Thomsen6, Jianbo Gao2,3,4

1Center for Humanities Computing, Aarhus University, Aarhus, Denmark; 2Center for Geodata and Analysis, Faculty of Geographical Science,\\ Beijing Normal University, Beijing, China; 3Institute of Automation, Chinese Academy of Sciences, Beijing, China; 4International College, Guangxi University, Nanning, Guangxi, China; 5Business School, Guangxi University, Nanning, Guangxi, China; 6School of Communication and Culture, Aarhus University, Aarhus, Denmark

The moods, feelings and attitudes represented in a novel will resonate in the reader by activating similar sentiments. It is generally accepted that sentiment analysis can capture aspects of such moods, feelings and attitudes and can be used to summarize a novel's plot in a story arc. With the availability of a number of algorithms that automatically extract sentiment-based story arcs, new approaches for their utilization becomes pertinent. We propose to use nonlinear adaptive filtering and fractal analysis in order to analyze the narrative coherence and dynamic evolution of a novel. Using Never Let Me Go by Kazuo Ishiguro, the winner of the 2017 Nobel Prize for Literature as an illustrative example, we illustrate how: 1) nonlinear adaptive filtering can extract a story arc that reflects the tragic trend of the novel; 2) the story arc displays persistent dynamics as measured by the Hurst exponent at short and medium time scales; and 3) the plot's dynamic evolution is reflected in the time-varying Hurst exponent. We argue that these findings are indicative of the potential that multifractal theory has for computational narratology and large-scale literary analysis. Specifically, that the global Hurst exponent of a story arc is an index of narrative coherence that can identify bland, incoherent and coherent narratives on a continuous scale. And, further, that the local time-varying Hurst exponent captures variation of a novel's plot such that the extrema have specific narratological interpretations.

Long Paper (20+10min)

Taking the Livonians into the Digital Space

Valts Ernštreits, Gunta Kļava

University of Latvia Livonian Institute, Latvia

Currently there are approximately 30 individuals who are able to communicate in Livonian (Livones) and approximately 250 individuals gave their ethnicity as “Livonian” on the last Latvian national census (Census 2011); however, the actual number of Livonians is considerably greater. Livonian heritage has had a significant, though understudied, role in the formation of modern Latvia, the Latvian language, and the Latvian nation, and has also been important across the broader Northern European region.

The Livonian community has been able to preserve its identity and also its language up to the present day despite its small size (19th century – 2500, mid-20th century – 1500) and the complicated history of the Livonian speech area (Druviete, Kļava 2018, 132). This history included the loss of the last compact Livonian-inhabited territory following the creation of a border zone along the Baltic Sea in the area encompassing the Livonian villages at the start of the Soviet occupation after World War II. As a result, the Livonians were scattered across Latvia and the world, and this fact continues to pose an added challenge for them. The same is true for various archives relating to Livonian (language, folklore, folk cultural objects, etc.), which for historical reasons were collected and therefore are currently stored at various institutions located in different countries (Ernštreits, 2012).

Though the number of Livonians and Livonian speakers is extremely small, the study of Livonian and related topics requires the same opportunities and tools as those for any other language. As a result, taking into account all of the aforementioned facts, the main issue faced by the Livonian community, Livonian researchers, and society at large is ease of access to sources and archives relating to Livonian heritage. The rapid digitalization of society during the last decades has created new opportunities for many smaller communities, including the Livonians, for solving these problems and designing new tools ensuring that these materials can be easily accessed and used.

Work on a Livonian language database cluster began in 2016 and currently contains three Livonian language databases – a lexical database, morphological database, and corpus – and consists of interconnected data archives. These databases have already significantly simplified the process for learning about, researching, and studying Livonian, and have created a foundation for future solutions directed towards simplifying access to Livonian-related materials. Though initially this system was created as a Livonian language data archive and a tool for language research, standardization, and acquisition, its principles also can be adjusted to suit other types of studies by supplementing it with other digital archives (containing images, audio recordings, video, 3D scans, data from other databases) as well as other information. A Livonian digital text archive, which is currently being built, will be one of these archives.

In 2019, the UL Livonian Institute submitted a project for expanding the existing Livonian language database cluster. This project takes the next logical step and will establish a mapped open-access Livonian place name database linked to geospatial information. This will open up radically new possibilities for access to various Livonian sources archives, ensure their availability for research as well as data interconnectedness in the future. The need for this project was initially due to practical considerations relating to collecting Livonian place names, so that bilingual road signs could be introduced in the territories historically inhabited by the Livonians.

There is no single Livonian place name archive. Livonian place names primarily are found in lexicographic publications or studies, albeit in a more scattered manner and fewer in number (for example, in the Livonian-Estonian-Latvian Dictionary (LELD), Livonian-German Dictionary (LW), the Livonian-Latvian-Esperanto Dictionary (ČDG), the Salaca Livonian Dictionary (SLW), and other lexicographic sources, in Kersti Boiko’s dissertation (Boiko 1993)). Currently, recording a large number of place names through field work is also not possible, as there remain only very few Livonian speakers and due to the historical situation of the Livonians, their connection with the territories inhabited by their ancestors is often indirect and their knowledge of Livonian place names is meagre. In large part, the Livonian language corpus is used instead of informants, and while indexing its contents, it is possible to not only identify Livonian place names, but also gain information regarding their localization.

At the same time there is a source, which is not a compilation of place names itself, but can be used effectively for collecting Livonian place names. This source consists of various collections – lexical card files, object card files and descriptions, folklore collections, etc. The metadata in these collections contain references to the time and method as well as the place where each item was collected and this information is usually shown in Livonian. It is also significant that places mentioned in this metadata are of specific importance to Livonian culture and are located within the historical Livonian territory to be documented and mapped for this project. These places are often not found in any available cartographic product (for example, homesteads which have disappeared or have been moved, drained rivers or lakes, etc.).

Therefore, the mapped place name database developed using metadata from various collections will serve as a starting point for the creation of a one-click database cluster. This will make it possible to link place names, geospatial data, and information data from other fields (e.g., information on consultants, dialect materials, objects, folklore, oral history collections, etc.), thereby opening up new possibilities for the multifaceted documentation and research of Livonian heritage in the future. Furthermore, this will make it possible to use data for many different purposes beyond research. These could include, for example, digital exhibits or using the cartographic products resulting from this project for education exploring regional heritage, cultural tourism, development of municipal strategies, entrepreneurship, and many other areas.

The products and discoveries resulting from this resource will also be useful to other smaller communities, and the synergy and coordination among various archives can create a rich, high-quality resource suitable for multi-faceted studies in many fields or for interdisciplinary research in general. It will also ensure effective use of data and research results for the preservation, maintenance, and development of any low-resource language or cultural community with limited data, personnel, financing, or other resources.


Boiko, Kersti (1993). Baltijas jūras somu ģeogrāfiskie apelatīvi un to relikti Latvijas vietvārdos (Balto-Finnic geographic words and their relicts in toponymy of Latvia). Disertācija filoloģijas doktora grāda iegūšanai. Latvijas Universitāte.

Census 2011 = Centrālā statistikas pārvalde. Tautas skaitīšana (Census), 2011. Available online at Accessed on 15.06.2019.

ČDG = Čače, Ints, Damberg, Pētõr, Grīva, Hilda (1964). Esperantisto en Latvio ce livoj = Esperantist Letmāl līvlist jūsõ. Manuscript. Rīga.

Druviete, Ina, Kļava, Gunta (2018). The role of Livonian in Latvia from a sociolinguistic perspective. Eesti ja soome-ugri keeleteaduse ajakiri = Journal of Estonian and Finno-Ugric Linguistics, Vol. 9, N 2, Livonian studies III, pp. 129–146. 10.12697/jeful.2018.9.2.06

Ernštreits, Valts (2012). Lībiešu valodas situācijas attīstība Latvijā. In I. Druviete (ed.) Valodas situācija Latvijā: 2004–2010. Rīga: Latviešu valodas aģentūra, pp. 142−166.

LELD = Līvõkīel-ēstikīel-lețkīel sõnārōntõz. Liivi-eesti-läti sõnaraamat. Lībiešu-igauņu-latviešu vārdnīca (2012). Tartu, Rīga: Tartu Ülikool, Latviešu valodas aģentūra.

Livones = Lībiešu valoda (Livonian language). Available online at Accessed on 15.06.2019.

LW = Joh. Andreas Sjögren’s Livisch–deutsches und deutsch–livisches Wörterbuch (1861). St. Petersburg: Kaiserlischen Akademie ded Wissenschaften.

SLW = Winkler, Eberhard, Pajusalu, Karl (2009). Salis-livisches Wörterbuch. Linguistica Uralica. Supplementary Series. Volume 3, Tallinn.