Topic modelling applied to a second language: A language adaptation and tool evaluation study

Skeppstedt, Maria; Ahltorp, Magnus; Kucher, Kostiantyn; Kerren, Andreas; Rzepka, Rafał; Araki, Kenji

doi:10.3384/ecp2020172017

Cited by 3 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Written languages for which this is not the case, for example, Japanese and Chinese, therefore require a pre-processing step where white space is inserted between tokens. 61 We have so far tested the functionality on texts written in English, Swedish, and Yiddish (using the Hebrew alphabet).…”

Section: Word Rain: Data Processing and Visual Encoding Stepsmentioning

confidence: 99%

From word clouds to Word Rain: Revisiting the classic word cloud to visualize climate change texts

Skeppstedt,

Ahltorp,

Kucher

et al. 2024

Information Visualization

View full text Add to dashboard Cite

Word Rain is a development of the classic word cloud. It addresses some of the limitations of word clouds, in particular the lack of a semantically motivated positioning of the words, and the use of font size as a sole indicator of word prominence. Word Rain uses the semantic information encoded in a distributional semantics-based language model – reduced into one dimension – to position the words along the x-axis. Thereby, the horizontal positioning of the words reflects semantic similarity. Font size is still used to signal word prominence, but this signal is supplemented with a bar chart, as well as with the position of the words on the y-axis. We exemplify the use of Word Rain by three concrete visualization tasks, applied on different real-world texts and document collections on climate change. In these case studies, word2vec models, reduced to one dimension with t-SNE, are used to encode semantic similarity, and TF-IDF is used for measuring word prominence. We evaluate the technique further by carrying out domain expert reviews.

show abstract

Section: Word Rain: Data Processing and Visual Encoding Stepsmentioning

confidence: 99%

From word clouds to Word Rain: Revisiting the classic word cloud to visualize climate change texts

Skeppstedt,

Ahltorp,

Kucher

et al. 2024

Information Visualization

View full text Add to dashboard Cite

show abstract

“…Firstly, in projects that try to program specific personality characteristics in robots that seemingly direct their decisions in improvised settings (Bruce et al, 2000;Magerko et al, 2010;Meerbeek et al, 2009;Skeppstedt & Ahltorp, 2018). Secondly, in projects that understand improvisation from an internal perspective, inasmuch as it is considered that the somatic and embodied knowledge that permits the improvisational act are located in the inner sphere of the human individual.…”

Section: A Theatre and Dance In Social Roboticsmentioning

confidence: 99%

Affective Movement in Robotic Art: Alternatives to the ‘Interiority Paradigm’ in Social Robotics

Troughton

2022

Body, Space &Amp; Technology

View full text Add to dashboard Cite

This papercritically evaluates how emotional and intentional movement is conceptualisedand deployed in social robotics and provides an alternative by analysingcontemporary robotic artworks that deal with affective human-robot interaction(HRI). Within HRI, movement as a way of communicating emotions and intent hasbecome a topic of increased interest, which has made social robotics turn totheatre and dance due to the expertise of these fields in expressive movement.This paper will argue that social robotics’ way of using performative methodswith regards to emotional movement is, nonetheless, limited and carries certainchallenges.  These challenges aregrounded on the claim that social robotics participates in what the authorcalls an ‘interiority paradigm’. That is, movement is understood to be theexpression of inner, pre-determined states. The 'interiority paradigm' poses several challenges to the development of emotional movement, with regards to unaddressed human androbotic imaginaries, an emphasis in legibility and familiarity, and arestrictive interior/exterior binary that limits the role of movement in anaffective connection. As an example of how robotscould be imagined beyond this interiority paradigm, the author proposes to turnto contemporary robotic art.Robotic art’s view on affective movement as a matter of evocationand of performative co-creation might inspire the development of robots thatmove beyond the requirement of being mere copies of a human interiority.  While the intersection between robotics andthe performing arts is a fruitful field of research, the author argues in thispaper that the way in which movement is currently being developed throughperformative methods has certain shortcomings, and that the perspective of roboticart on affective movement might open up a more interesting area of explorationfor social robotics, as well as expose those aspects of theatre and dance thathave being unaddressed in robotics. 

show abstract

Framing climate change in Nature and Science editorials: applications of supervised and unsupervised text categorization

et al. 2023

View full text Add to dashboard Cite

Hulme et al. (Nat Clim Change, 8:515–521, 2018) manually coded ‘frames’ in 490 Nature and Science editorials (1966–2016) they found relevant for climate change. We produced a digital version of the corpus and conducted a set of experiments: We explored many variants of supervised categorization for automatically reproducing the manual frame coding, and we ran an interactive variant of topic modeling. In both approaches, we made use of word embedding techniques for representing text documents. Supervised classification yielded F1-scores of up to 0.91 (for the best category) and 0.68 overall, and it led to insights regarding the relation between ‘topic’ and ‘framing’. The topic modeling algorithm was able to reproduce central trends in the temporal analysis of framing that was presented by Hulme et al. based on their manual work.

show abstract

Topic modelling applied to a second language: A language adaptation and tool evaluation study

Cited by 3 publications

References 17 publications

From word clouds to Word Rain: Revisiting the classic word cloud to visualize climate change texts

From word clouds to Word Rain: Revisiting the classic word cloud to visualize climate change texts

Affective Movement in Robotic Art: Alternatives to the ‘Interiority Paradigm’ in Social Robotics

Framing climate change in Nature and Science editorials: applications of supervised and unsupervised text categorization

Contact Info

Product

Resources

About