Search

This study is intended to provide in-depth insights into how design thinking and creativity issues are understood and possibly evolve in the course of design discussions in a company context. For that purpose, we use the seminar transcripts of the Design Thinking Research Symposium 12 (DTRS12) dataset “Tech-centred Design Thinking: Perspectives from a Rising Asia,” which are primarily concerned with how Korean companies implement design thinking and what role designers currently play. We employed a novel method of information processing based on constructed dynamic semantic networks to investigate the seminar discussions according to company representatives and company size. We compared the quantitative dynamics in two seminars: the first involved managerial representatives of four companies, and the second involved specialized designers and management of a design center of single company. On the basis of dynamic semantic networks, we quantified the changes in four semantic measures—abstraction, polysemy, information content, and pairwise word similarity—in chronologically reconstructed individual design-thinking processes. Statistical analyses show that design thinking in the seminar with four companies, exhibits significant differences in the dynamics of abstraction, polysemy, and information content, compared to the seminar with the design center of single company. Both the decrease in polysemy and abstraction and the increase in information content in the individual design-thinking processes in the seminar with four companies indicate that design managers are focused on more concrete design issues, with more information and less ambiguous content to the final design product. By contrast, specialized designers manifest more abstract thinking and appear to exhibit a slightly higher level of divergence in their design processes. The results suggest that design thinking and creativity issues are articulated differently depending on designer roles and the co

Within personality research, self-report questionnaires are a common approach. This study takes aim at investigating whether self-report questionnaires are enough, or if semantic measures, through Natural Language Processing, could be a substitute or complementary method, in assessing personality. Based on the Five Factor Model of personality, this study has been divided into two phases. Participants originating from the U.S. were instructed to either describe and rate their own or someone else's personality (Phase 1, N=264), or read personality narratives from Phase 1 (Phase 2, N=399) then, in both phases, participants were asked to answer a semantic question as well as a IPIP-NEO rating scale. Prediction scores from the two phases were used to analyze semantic measures in comparison to rating scales. The results suggest that semantic measures, on their own, categorize personality traits more accurately (53%) than rating scales (44%). To conclude, complementary approaches while assessing personality have shown to be of great value. Future research would be benefitted by investigating the possibility of applying this method in other fields of psychology, in favor of further assessing the method's validity, and determining whether it can offer novel understandings of constructs.

La detección de emociones es una tarea del análisis de sentimientos que trata la extracción y el análisis de las emociones en textos. Reconocer emociones implícitas es uno de los principales desafíos en enfoques basados en palabras claves o lexicones. Este trabajo presenta un enfoque híbrido de detección de emociones, que combina la selección de características relevantes de emoción basada en un lexicón, con un enfoque clásico de aprendizaje para determinar la emoción. El proceso de selección de características propuesto se centra en capturar el significado emocional del texto mediante el cálculo de la relación semántica entre su contenido y el vocabulario del lexicón, con el objetivo de incrementar el reconocimiento de emociones implícitas. La solución propuesta fue evaluada en la clasificación de emociones en tweets en español incluidos en el corpus AIT, con diferentes alternativas para computar la relación semántica y varios algoritmos de clasificación, obteniéndose resultados muy prometedores., Emotion detection is a task of sentiment analysis that deals with the extraction and analysis of emotions in texts. Recognizing implicit emotions is one of the main challenges in keyword or lexicon-based approaches. This paper presents a hybrid emotion detection approach, which combines lexicon-based emotion-relevant feature selection with a classical learning-based approach to determine the emotion. The proposed feature selection process focuses on capturing the emotional meaning of the text by computing the semantic relationship between its content and the lexicon vocabulary, with the goal of increasing implicit emotion recognition. The proposed solution was evaluated on the classification of emotions in Spanish tweets included in the AIT corpus, with different alternatives to compute the semantic relation and several classification algorithms, obtaining very promising results.

The analysis of conversations during design activity can facilitate deeper insights into design thinking and its relation to creativity. A semantic analysis approach was employed to explore the semantic content of communication and information exchange between students and instructors. The goal was to examine design conversations in terms of abstraction, Polysemy, Information Content, and Semantic Similarity measures, and analyze their relation to the creativity of final solutions. These design outcomes were assessed according to their Originality, Usability, Feasibility, Overall Value, and Overall Creativity. Consequently, 35 design conversations from the 10th Design Thinking Research Symposium (DTRS10) dataset were analyzed. The main results showed that Information Content and Semantic Similarity predicted Originality, and Information Content alone predicted Overall Creativity. Likewise, Abstraction predicted Feasibility, while Semantic Similarity, Information Content, and Polysemy predicted Overall Value. In context of instructors, Semantic Similarity predicted Usability, and Polysemy predicted Feasibility. For students, Semantic Similarity predicted Overall Value. On the whole, Semantic Similarity and Information Content were the most prolific measures, and therefore could be considered for promoting creativity in the design studio. The implications of using support tools such as automated systems are also discussed.

La detección de emociones es una tarea del análisis de sentimientos que trata la extracción y el análisis de las emociones en textos. Reconocer emociones implícitas es uno de los principales desafíos en enfoques basados en palabras claves o lexicones. Este trabajo presenta un enfoque híbrido de detección de emociones, que combina la selección de características relevantes de emoción basada en un lexicón, con un enfoque clásico de aprendizaje para determinar la emoción. El proceso de selección de características propuesto se centra en capturar el significado emocional del texto mediante el cálculo de la relación semántica entre su contenido y el vocabulario del lexicón, con el objetivo de incrementar el reconocimiento de emociones implícitas. La solución propuesta fue evaluada en la clasificación de emociones en tweets en español incluidos en el corpus AIT, con diferentes alternativas para computar la relación semántica y varios algoritmos de clasificación, obteniéndose resultados muy prometedores., Emotion detection is a task of sentiment analysis that deals with the extraction and analysis of emotions in texts. Recognizing implicit emotions is one of the main challenges in keyword or lexicon-based approaches. This paper presents a hybrid emotion detection approach, which combines lexicon-based emotion-relevant feature selection with a classical learning-based approach to determine the emotion. The proposed feature selection process focuses on capturing the emotional meaning of the text by computing the semantic relationship between its content and the lexicon vocabulary, with the goal of increasing implicit emotion recognition. The proposed solution was evaluated on the classification of emotions in Spanish tweets included in the AIT corpus, with different alternatives to compute the semantic relation and several classification algorithms, obtaining very promising results.

Work takes up a lot of our time and a third of our lives. The purpose of this study is to examine how an individual’s view of their work relates to their well-being. The study uses a survey to explore what views of the job that the participants (N = 240) have. Job satisfaction was measured with semantic measures, that is open-ended questions analysed with AI, and the Generic Job satisfaction Scale. The Satisfaction With Life Scale and the Harmony In Life Scale measured participants’ well-being. Analyses of the semantic measures showed that words such as money described job satisfaction and stress described dissatisfaction (t(2630)=46.48, p<.001). The semantic similarity scores between described personal job satisfaction and a job satisfaction word norm (participant generated text that describes high job satisfaction) correlated with the Generic Job Satisfaction scale (r = .55) the strongest; hence this can be seen as a new word-based measure of job satisfaction, as an alternative to numeric scales. The semantic similarity scores correlated significantly with all numeric scales (r = .35 to r = .55, p<.001) and word-responses significantly predicted numeric scales (r = .38 to r =.58, p<.001). Participants described their job-satisfaction with words such as rewarding, happy and challenging. The study demonstrates how a person’s view of their work is connected to their subjective well-being., Arbetet tar upp mycket av vår tid och en tredjedel av våra liv. Syftet med denna studie är att undersöka hur en individs syn på sitt arbete relaterar till deras välbefinnande. Studien använder en enkät för att undersöka vilka synpunkter på jobbet deltagarna (N = 240) har. Arbetstillfredsställelse mättes med semantiska mätningar, som är öppna frågor analyserade med AI, och med Generic Job Satisfaction Scale. Satisfaction With Life Scale och Harmony In Life Scale mätte deltagarnas välbefinnande. Analyser av de semantiska måtten visade att ord som pengar beskrev arbetstillfredsställelse och stress beskrev arbetsotillfredsställelse (t (2630) = 46,48, p <0,001). De semantiska likhetspoängen mellan beskrivna personliga arbetstillfredsställelsen och en ordnorm för arbetstillfredsställelse (text genererad av deltagare som beskriver hög arbetstillfredsställelse) korrelerade med Generic Job Satisfaction Scale(r = .55) starkast; därför kan detta ses som ett nytt ordbaserat mått på arbetstillfredsställelse, som ett alternativ till numeriska skalor. De semantiska likhetspoängen korrelerade signifikant med alla numeriska skalor (r = .35 till r = .55, p <.001) och ordsvar predicerade signifikant de numeriska skalorna (r = .38 till r = .58, p <.001). Deltagarna beskrev sin arbetstillfredsställelse med ord som givande, glad och utmanande. Studien visar hur en persons syn på sitt arbete är kopplat till deras subjektiva välbefinnande.

The analysis of conversations maintained during the design activity can help to gain a better insight into design thinking and its relation to creativity. A semantic analysis approach was employed to inspect the content of communications and information exchange between students and instructors. The goal was to explore design conversations in terms of Abstraction, Polysemy, Information Content and Semantic Similarity measures, and analyse their relation to the creativity of final design outcomes. These were assessed according to their Originality, Usability, Feasibility, Overall Value and Overall Creativity. To this end, design conversations from the 10th Design Thinking Research Symposium (DTRS10) dataset were used. Main results show a significant relationship between Information Content and Originality and Overall Creativity. For instructors, Semantic measures were mainly related to Feasibility, whereas for students the focus was set on the Overall Value of the final solutions.

Work takes up a lot of our time and a third of our lives. The purpose of this study is to examine how an individual’s view of their work relates to their well-being. The study uses a survey to explore what views of the job that the participants (N = 240) have. Job satisfaction was measured with semantic measures, that is open-ended questions analysed with AI, and the Generic Job satisfaction Scale. The Satisfaction With Life Scale and the Harmony In Life Scale measured participants’ well-being. Analyses of the semantic measures showed that words such as money described job satisfaction and stress described dissatisfaction (t(2630)=46.48, p<.001). The semantic similarity scores between described personal job satisfaction and a job satisfaction word norm (participant generated text that describes high job satisfaction) correlated with the Generic Job Satisfaction scale (r = .55) the strongest; hence this can be seen as a new word-based measure of job satisfaction, as an alternative to numeric scales. The semantic similarity scores correlated significantly with all numeric scales (r = .35 to r = .55, p<.001) and word-responses significantly predicted numeric scales (r = .38 to r =.58, p<.001). Participants described their job-satisfaction with words such as rewarding, happy and challenging. The study demonstrates how a person’s view of their work is connected to their subjective well-being., Arbetet tar upp mycket av vår tid och en tredjedel av våra liv. Syftet med denna studie är att undersöka hur en individs syn på sitt arbete relaterar till deras välbefinnande. Studien använder en enkät för att undersöka vilka synpunkter på jobbet deltagarna (N = 240) har. Arbetstillfredsställelse mättes med semantiska mätningar, som är öppna frågor analyserade med AI, och med Generic Job Satisfaction Scale. Satisfaction With Life Scale och Harmony In Life Scale mätte deltagarnas välbefinnande. Analyser av de semantiska måtten visade att ord som pengar beskrev arbetstillfredsställelse och stress beskrev arbetsotillfredsställelse (t (2630) = 46,48, p <0,001). De semantiska likhetspoängen mellan beskrivna personliga arbetstillfredsställelsen och en ordnorm för arbetstillfredsställelse (text genererad av deltagare som beskriver hög arbetstillfredsställelse) korrelerade med Generic Job Satisfaction Scale(r = .55) starkast; därför kan detta ses som ett nytt ordbaserat mått på arbetstillfredsställelse, som ett alternativ till numeriska skalor. De semantiska likhetspoängen korrelerade signifikant med alla numeriska skalor (r = .35 till r = .55, p <.001) och ordsvar predicerade signifikant de numeriska skalorna (r = .38 till r = .58, p <.001). Deltagarna beskrev sin arbetstillfredsställelse med ord som givande, glad och utmanande. Studien visar hur en persons syn på sitt arbete är kopplat till deras subjektiva välbefinnande.

Vi rör oss ständigt i offentliga rum som på olika sätt är utformade för att påverka oss. Denna studie undersöker om människors känslor, syn på välbefinnande och syn på meningen med livet påverkas av att befinna sig i olika rum, i detta fall en kyrka (N=51) och ett köpcenter (N=51). Två verktyg, semantiska mått och Positive and Negative Affect Schedule (PANAS) används för att undersöka om det finns en skillnad i vilka känslor som studiens deltagare upplever beroende på rum. Deltagarna svarade på öppna semantiska frågor med fritt valda beskrivande ord och genom att fylla i traditionella skattningsskalor i antingen en kyrka eller ett köpcentrum. Analyser genomfördes med statistik och artificiell intelligens. Det fanns en signifikant skillnad i valens, där kyrkan hade en signifikant högre positiv valens i svaren än köpcentret (t=-3,17, p=0,002, two-tailed, Cohen’s D=0,63). Deltagarnas känslor skiljde sig signifikant i de semantiska måtten och uppvisade en stor effektstorlek (t=5.43, p=0,001, Cohens D=0.76). PANAS visade inte en signifikant skillnad i positiva (t(102) =1,82, p=0,072, one-tail, Cohens D=0,37) eller negativa känslor (t (102) =-1,64, p=0,103, one-tailed, Cohens D=0,26). Denna studie indikerar att de att rum som vi befinner oss i påverkar våra känslor., We are constantly moving between environments that are designed to affect us in one way or another. The purpose of this study is to investigate if the room has an influence on people's feelings, and their views on well-being and meaning of life. In a randomised experiment, the study explores whether there is a measurable difference in the participants’ feelings and thoughts in a church (n=51) and a shopping mall (n=51). In this study, open-ended questions with word responses (semantic measures) are used together with Positive and Negative Affect Schedule (PANAS) to measure participants’ feelings. Frequentist statistics and artificial intelligence were used to analyse the data. Analyses of the semantic measures showed that words written in the church had a significantly more positive valence than words written in the shopping mall (t=-3,17, p=,002, two-tailed, Cohen’s D=0,63), and that the participants’ word responses for feelings differed significantly with a large effect size (t=5.43, p=,001, Cohen’s D=0.76). PANAS did not show any significant difference in the participants’ positive (t(102) =1,82, p=,072, one-tail, Cohens D=0,37) or negative feelings (t (102) =-1,64, p=,103, one-tailed, Cohens D=0,26). This study indicates that the rooms we spend time in has an effect on our feelings.

Vi rör oss ständigt i offentliga rum som på olika sätt är utformade för att påverka oss. Denna studie undersöker om människors känslor, syn på välbefinnande och syn på meningen med livet påverkas av att befinna sig i olika rum, i detta fall en kyrka (N=51) och ett köpcenter (N=51). Två verktyg, semantiska mått och Positive and Negative Affect Schedule (PANAS) används för att undersöka om det finns en skillnad i vilka känslor som studiens deltagare upplever beroende på rum. Deltagarna svarade på öppna semantiska frågor med fritt valda beskrivande ord och genom att fylla i traditionella skattningsskalor i antingen en kyrka eller ett köpcentrum. Analyser genomfördes med statistik och artificiell intelligens. Det fanns en signifikant skillnad i valens, där kyrkan hade en signifikant högre positiv valens i svaren än köpcentret (t=-3,17, p=0,002, two-tailed, Cohen’s D=0,63). Deltagarnas känslor skiljde sig signifikant i de semantiska måtten och uppvisade en stor effektstorlek (t=5.43, p=0,001, Cohens D=0.76). PANAS visade inte en signifikant skillnad i positiva (t(102) =1,82, p=0,072, one-tail, Cohens D=0,37) eller negativa känslor (t (102) =-1,64, p=0,103, one-tailed, Cohens D=0,26). Denna studie indikerar att de att rum som vi befinner oss i påverkar våra känslor., We are constantly moving between environments that are designed to affect us in one way or another. The purpose of this study is to investigate if the room has an influence on people's feelings, and their views on well-being and meaning of life. In a randomised experiment, the study explores whether there is a measurable difference in the participants’ feelings and thoughts in a church (n=51) and a shopping mall (n=51). In this study, open-ended questions with word responses (semantic measures) are used together with Positive and Negative Affect Schedule (PANAS) to measure participants’ feelings. Frequentist statistics and artificial intelligence were used to analyse the data. Analyses of the semantic measures showed that words written in the church had a significantly more positive valence than words written in the shopping mall (t=-3,17, p=,002, two-tailed, Cohen’s D=0,63), and that the participants’ word responses for feelings differed significantly with a large effect size (t=5.43, p=,001, Cohen’s D=0.76). PANAS did not show any significant difference in the participants’ positive (t(102) =1,82, p=,072, one-tail, Cohens D=0,37) or negative feelings (t (102) =-1,64, p=,103, one-tailed, Cohens D=0,26). This study indicates that the rooms we spend time in has an effect on our feelings.

One key feature of the Semantic Web lies in the ability to link related Web resources. However, while relations within particular datasets are often well-defined, links between disparate datasets and corpora of Web resources are rare. The increasingly widespread use of cross-domain reference datasets, such as Freebase and DBpedia for annotating and enriching datasets as well as documents, opens up opportunities to exploit their inherent semantic relationships to align disparate Web resources. In this paper, we present a combined approach to uncover relationships between disparate entities which exploits (a) graph analysis of reference datasets together with (b) entity co-occurrence on the Web with the help of search engines. In (a), we introduce a novel approach adopted and applied from social network theory to measure the connectivity between given entities in reference datasets. The connectivity measures are used to identify connected Web resources. Finally, we present a thorough evaluation of our approach using a publicly available dataset and introduce a comparison with established measures in the field. The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-38288-8_37.