SemanticExcel.com: An Online Software for Statistical Analyses of Text Data Based on Natural Language Processing

Sikström, Sverker; Kjell, Oscar; Kjell, Katarina

doi:10.1007/978-3-030-37250-7_6

Cited by 12 publications

(15 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For methodological details, and how the models can be used to predict a numerical value and optimization, we refer to other articles (e.g., Landauer, 1999 ; Kjell et al, 2018 ) and the Appendix . The data analysis was conducted in SemanticExcel, which is an online statistical software application that analyzes texts that allows calling the LSA model and the BERT model that is described elsewhere (e.g., Sikström et al, 2020 ; Sikström and Garcia, 2020 ). Finally, the source code for the LSA analysis is available on Github.…”

Section: Methodsmentioning

confidence: 99%

Language and gender: Computerized text analyses predict gender ratios from organizational descriptions

Stille

Sikström²,

Lindqvist³

et al. 2023

Front. Psychol.

Self Cite

View full text Add to dashboard Cite

Previous research has shown that language in job adverts implicitly communicates gender stereotypes, which, in turn, influence employees’ perceived fit with the job. In this way, language both reflects and maintains a gender segregated job market. The aim of this study was to test whether, and how, language in organizational descriptions reflects gender segregation in the organizations by the use of computational text analyses. We analyzed large Swedish companies’ organizational descriptions from LinkedIn (N = 409), testing whether the language in the organizational descriptions is associated with the organizations’ employee gender ratio, and how organizational descriptions for organizations with a majority of women and men employees differ. The statistical analyses showed that language in the organizational descriptions predicted the employee gender ratio in organizations well. Word clouds depicting words that differentiate between organizations with a majority of women and men employees showed that the language of organizations with a higher percentage of women employees was characterized by a local focus and emphasis on within-organizations relations, whereas the language of organizations with a higher percentage of men employees was characterized by an international focus and emphasis on sales and customer relations. These results imply that the language in organizational descriptions reflects gender segregation and stereotypes that women are associated with local and men with global workplaces. As language communicates subtle signals in regards to what potential candidate is most sought after in recruitment situations, differences in organizational descriptions can hinder underrepresented gender groups to apply to these jobs. As a consequence, such practices may contribute to gender segregation on the job market.

show abstract

Section: Methodsmentioning

confidence: 99%

Language and gender: Computerized text analyses predict gender ratios from organizational descriptions

Stille

Sikström²,

Lindqvist³

et al. 2023

Front. Psychol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…This method is described in detail by Kjell et al [ 33 ], and here we provide a brief overview of the algorithm. The analysis was conducted using an online platform for statistical analysis of semantic representations called SemanticExcel, which is developed by the author of this paper [ 35 ].…”

Section: Methodsmentioning

confidence: 99%

Removing Biases in Communication of Severity Assessments of Intimate Partner Violence: Model Development and Evaluation

Claesdotter-Knutsson¹,

Dahl²,

Sikström³

2023

J Med Internet Res

View full text Add to dashboard Cite

Background To support a victim of violence and establish the correct penalty for the perpetrator, it is crucial to correctly evaluate and communicate the severity of the violence. Recent data have shown these communications to be biased. However, computational language models provide opportunities for automated evaluation of the severity to mitigate the biases. Objective We investigated whether these biases can be removed with computational algorithms trained to measure the severity of violence described. Methods In phase 1 (P1), participants (N=71) were instructed to write some text and type 5 keywords describing an event where they experienced physical violence and 1 keyword describing an event where they experienced psychological violence in an intimate partner relationship. They were also asked to rate the severity. In phase 2 (P2), another set of participants (N=40) read the texts and rated them for severity of violence on the same scale as in P1. We also quantified the text data to word embeddings. Machine learning was used to train a model to predict the severity ratings. Results For physical violence, there was a greater accuracy bias for humans (r2=0.22) compared to the computational model (r2=0.31; t38=–2.37, P=.023). For psychological violence, the accuracy bias was greater for humans (r2=0.058) than for the computational model (r2=0.35; t38=–14.58, P<.001). Participants in P1 experienced psychological violence as more severe (mean 6.46, SD 1.69) than participants rating the same events in P2 (mean 5.84, SD 2.80; t86=–2.22, P=.029<.05), whereas no calibration bias was found for the computational model (t134=1.30, P=.195). However, no calibration bias was found for physical violence for humans between P1 (mean 6.59, SD 1.81) and P2 (mean 7.54, SD 2.62; t86=1.32, P=.19) or for the computational model (t134=0.62, P=.534). There was no difference in the severity ratings between psychological and physical violence in P1. However, the bias (ie, the ratings in P2 minus the ratings in P1) was highly negatively correlated with the severity ratings in P1 (r2=0.29) and in P2 (r2=0.37), whereas the ratings in P1 and P2 were somewhat less correlated (r2=0.11) using the psychological and physical data combined. Conclusions The results show that the computational model mitigates accuracy bias and removes calibration biases. These results suggest that computational models can be used for debiasing the severity evaluations of violence. These findings may have application in a legal context, prioritizing resources in society and how violent events are presented in the media.

show abstract

“…That is, for context-free representations, the word "bank" has the same representation in "bank account" and "river bank". The context-free pre-trained model in this study comes from Semantic Excel (English Space 1) 24,25 ; the model has been produced using Latent Semantic Analysis 10 applied to text from the Google N-gram database (https://books.google.com/ngrams).…”

Section: Analytic Methodsmentioning

confidence: 99%

Natural Language Analyzed with AI-based Transformers Predict Traditional Well-Being Measures Approaching the Theoretical Upper Limits in Accuracy

Kjell¹,

Sikström²,

Kjell³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We show that using a recent break-through in artificial intelligence –transformers–, psychological assessments from text-responses can approach theoretical upper limits in accuracy, converging with standard psychological rating scales. Text-responses use people's primary form of communication –natural language– and have been suggested as a more ecologically-valid response format than closed-ended rating scales that dominate social science. However, previous language analysis techniques left a gap between how accurately they converged with standard rating scales and how well ratings scales converge with themselves – a theoretical upper-limit in accuracy. Most recently, AI-based language analysis has gone through a transformation as nearly all of its applications, from Web search to personalized assistants (e.g., Alexa and Siri), have shown unprecedented improvement by using transformers. We evaluate transformers for estimating psychological well-being from questionnaire text- and descriptive word-responses, and find accuracies converging with rating scales that approach the theoretical upper limits (Pearson r = .85, p < .001, N = 608; in line with most metrics of rating scale reliability). These findings suggest an avenue for modernising the ubiquitous questionnaire and ultimately opening doors to a greater understanding of the human condition.

show abstract

SemanticExcel.com: An Online Software for Statistical Analyses of Text Data Based on Natural Language Processing

Cited by 12 publications

References 6 publications

Language and gender: Computerized text analyses predict gender ratios from organizational descriptions

Language and gender: Computerized text analyses predict gender ratios from organizational descriptions

Removing Biases in Communication of Severity Assessments of Intimate Partner Violence: Model Development and Evaluation

Natural Language Analyzed with AI-based Transformers Predict Traditional Well-Being Measures Approaching the Theoretical Upper Limits in Accuracy

Contact Info

Product

Resources

About