On the polysemy of the Polish complete path construction: A corpus-based exploratory study

2019 ◽  
Vol 55 (4) ◽  
pp. 631-670
Author(s):  
Daria Bębeniec ◽  
Małgorzata Cudna
Keyword(s):  
Cluster Analysis ◽  
Random Sample ◽  
Exploratory Study ◽  
Semantic Features ◽  
Hierarchical Agglomerative Cluster ◽  
Usage Patterns ◽  
Complete Path ◽  
Hierarchical Agglomerative Cluster Analysis ◽  
National Corpus

Abstract In this article, we present a corpus-based analysis of two major types of the Polish Complete Path (CP) construction in which a source-PP, headed by od+GEN, is immediately followed by a goal-PP, headed by do+GEN or po+ACC, as in od jesieni 1920 do jesieni 1921 ‘from autumn 1920 to autumn 1921’ and od kreskówek po rysunki techniczne ‘from cartoons to technical drawings’. The aim of the study is to shed some light on the polysemous structure of the CP construction on the basis of its usage patterns. To this end, we used a random sample of over 500 instances of both construction types retrieved from the National Corpus of Polish. The data were annotated for a number formal and semantic features and subsequently explored using hierarchical agglomerative cluster analysis. When interpreting the results of several analyses performed on different sets of variables, we gave special attention to three levels of semantic granularity encoded in the data, concluding that, on the whole, all analyses point towards a distinction between the spatial, temporal and abstract meanings of the construction under investigation.

TTO characteristics and university entrepreneurship: a cluster analysis

2019 ◽  
Vol 10 (4) ◽  
pp. 861-889 ◽  
Author(s):  
Mariluz Fernandez-Alles ◽  
Juan Pablo Diánez-González ◽  
Tamara Rodríguez-González ◽  
Mercedes Villanueva-Flores
Keyword(s):  
Cluster Analysis ◽  
Efficient Design ◽  
Content Type ◽  
University Entrepreneurship ◽  
Multivariate Technique ◽  
Hierarchical Agglomerative Cluster ◽  
Technology Transfer Offices ◽  
Design Characteristics ◽  
The Relationship ◽  
Hierarchical Agglomerative Cluster Analysis

Purpose The purpose of this paper is to analyze potentially significant differences in a series of relevant characteristics of universities’ technology transfer offices (TTOs). To this end, TTOs have been classified by the function of their resources assigned to the enhancement of university entrepreneurship. The factors analyzed are the number of academic spin-offs created with the support of TTOs as well as the TTOs’ age, experience, professionalization and relational capital. Design/methodology/approach The authors have performed a hierarchical agglomerative cluster analysis to identify the groups of TTOs with homogeneous behavior and features. This multivariate technique allows determining whether it is possible to identify some differentiated conglomerates of TTOs. Findings The results of the cluster analysis allow concluding that the number of academic spin-offs created with the support of TTOs, the age and degree of professionalization of these TTOs, the experiences of their employees in matters related to entrepreneurship and their relationships with market actors explain the different levels of commitment of TTOs toward the enhancement of university entrepreneurship. In contrast with the expected results, the relationship between TTOs and academic actors does not seem to explain such differences. Originality/value This research contributes to the identification of the particular design characteristics that TTOs should exhibit to promote the entrepreneurial performance of universities, offering important recommendations to academic institutions regarding the efficient design of TTOs to manage university ambidexterity and to build TTOs’ entrepreneurial identity.

scholarly journals Cluster Analysis of Haze Episodes Based on Topological Features

2020 ◽  
Vol 12 (10) ◽  
pp. 3985
Author(s):  
Nur Fariha Syaqina Zulkepli ◽  
Mohd Salmi Md Noorani ◽  
Fatimah Abdul Razak ◽  
Munira Ismail ◽  
Mohd Almie Alias
Keyword(s):  
Cluster Analysis ◽  
Persistent Homology ◽  
Topological Data Analysis ◽  
Data Sets ◽  
Air Quality Monitoring ◽  
Hierarchical Agglomerative Cluster ◽  
Topological Features ◽  
Hidden Patterns ◽  
Air Quality Monitoring Stations ◽  
Hierarchical Agglomerative Cluster Analysis

Severe haze episodes have periodically occurred in Southeast Asia, specifically taunting Malaysia with adverse effects. A technique called cluster analysis was used to analyze these occurrences. Traditional cluster analysis, in particular, hierarchical agglomerative cluster analysis (HACA), was applied directly to data sets. The data sets may contain hidden patterns that can be explored. In this paper, this underlying information was captured via persistent homology, a topological data analysis (TDA) tool, which extracts topological features including components, holes, and cavities in the data sets. In particular, an improved version of HACA was proposed by combining HACA and persistent homology. Additionally, a comparative study between traditional HACA and improved HACA was done using particulate matter data, which was the major pollutant found during haze episodes by the Klang, Petaling Jaya, and Shah Alam air quality monitoring stations. The effectiveness of these two clustering approaches was evaluated based on their ability to cluster the months according to the haze condition. The results showed that clustering based on topological features via the improved HACA approach was able to correctly group the months with severe haze compared to clustering them without such features, and these results were consistent for all three locations.

scholarly journals Evaluation of hierarchical agglomerative cluster analysis methods for discrimination of primary biological aerosol

2015 ◽  
Vol 8 (11) ◽  
pp. 4979-4991 ◽  
Author(s):  
I. Crawford ◽  
S. Ruske ◽  
D. O. Topping ◽  
M. W. Gallagher
Keyword(s):  
Cluster Analysis ◽  
Asymmetry Factor ◽  
Z Score ◽  
Desktop Computer ◽  
Data Set ◽  
Hierarchical Agglomerative Cluster ◽  
Bacterial Aerosol ◽  
Ambient Data ◽  
Spectrometer Data ◽  
Hierarchical Agglomerative Cluster Analysis

Abstract. In this paper we present improved methods for discriminating and quantifying primary biological aerosol particles (PBAPs) by applying hierarchical agglomerative cluster analysis to multi-parameter ultraviolet-light-induced fluorescence (UV-LIF) spectrometer data. The methods employed in this study can be applied to data sets in excess of 1 × 106 points on a desktop computer, allowing for each fluorescent particle in a data set to be explicitly clustered. This reduces the potential for misattribution found in subsampling and comparative attribution methods used in previous approaches, improving our capacity to discriminate and quantify PBAP meta-classes. We evaluate the performance of several hierarchical agglomerative cluster analysis linkages and data normalisation methods using laboratory samples of known particle types and an ambient data set. Fluorescent and non-fluorescent polystyrene latex spheres were sampled with a Wideband Integrated Bioaerosol Spectrometer (WIBS-4) where the optical size, asymmetry factor and fluorescent measurements were used as inputs to the analysis package. It was found that the Ward linkage with z-score or range normalisation performed best, correctly attributing 98 and 98.1 % of the data points respectively. The best-performing methods were applied to the BEACHON-RoMBAS (Bio–hydro–atmosphere interactions of Energy, Aerosols, Carbon, H2O, Organics and Nitrogen–Rocky Mountain Biogenic Aerosol Study) ambient data set, where it was found that the z-score and range normalisation methods yield similar results, with each method producing clusters representative of fungal spores and bacterial aerosol, consistent with previous results. The z-score result was compared to clusters generated with previous approaches (WIBS AnalysiS Program, WASP) where we observe that the subsampling and comparative attribution method employed by WASP results in the overestimation of the fungal spore concentration by a factor of 1.5 and the underestimation of bacterial aerosol concentration by a factor of 5. We suggest that this likely due to errors arising from misattribution due to poor centroid definition and failure to assign particles to a cluster as a result of the subsampling and comparative attribution method employed by WASP. The methods used here allow for the entire fluorescent population of particles to be analysed, yielding an explicit cluster attribution for each particle and improving cluster centroid definition and our capacity to discriminate and quantify PBAP meta-classes compared to previous approaches.

scholarly journals Towards a dynamic behavioral profile: A diachronic study of polysemous sentir in Spanish

2020 ◽  
Vol 16 (1) ◽  
pp. 145-187 ◽  
Author(s):  
Marlies Jansegers ◽  
Stefan Th. Gries
Keyword(s):  
Cluster Analysis ◽  
Multidimensional Scaling ◽  
Historical Data ◽  
Discourse Marker ◽  
Behavioral Profile ◽  
Hierarchical Agglomerative Cluster ◽  
Historical Semantics ◽  
Diachronic Study ◽  
Hierarchical Agglomerative Cluster Analysis

AbstractThis study examines the diachronic evolution of the polysemy of the Spanish verbsentir(‘to feel’) by means of a corpus-based dynamic behavioral profile (BP) analysis. Methodologically, it presents the first application of the BP approach to historical data and proposes some methodological innovations not only within the current body of research in historical semantics but also with regard to previous applications of the BP approach. First, whereas the majority of existing studies in quantitative historical semantics are largely based on observed frequencies or percentages of collocational co-occurrence, our study leverages more complex historical data that are based on the similarities of vectors. Second, this study also provides an extension of the methodological apparatus of the BP approach by complementing the traditional hierarchical agglomerative cluster analysis (HAC) with a dynamic BP approach derived from multidimensional scaling maps (MDS). Theoretically, this methodology contributes to a comprehensive perspective on the process of Constructionalization and the nature of networks, which is illustrated on the basis of the development of the Discourse Marker (DM)lo siento(‘I’m sorry’).

scholarly journals Evaluation of hierarchical agglomerative cluster analysis methods for discrimination of primary biological aerosol

2015 ◽  
Vol 8 (7) ◽  
pp. 7303-7333 ◽  
Author(s):  
I. Crawford ◽  
S. Ruske ◽  
D. O. Topping ◽  
M. W. Gallagher
Keyword(s):  
Cluster Analysis ◽  
Fungal Spores ◽  
Polystyrene Latex ◽  
Asymmetry Factor ◽  
Z Score ◽  
Desktop Computer ◽  
Hierarchical Agglomerative Cluster ◽  
Bacterial Aerosol ◽  
Spectrometer Data ◽  
Hierarchical Agglomerative Cluster Analysis

Abstract. In this paper we present improved methods for discriminating and quantifying Primary Biological Aerosol Particles (PBAP) by applying hierarchical agglomerative cluster analysis to multi-parameter ultra violet-light induced fluorescence (UV-LIF) spectrometer data. The methods employed in this study can be applied to data sets in excess of 1×106 points on a desktop computer, allowing for each fluorescent particle in a dataset to be explicitly clustered. This reduces the potential for misattribution found in subsampling and comparative attribution methods used in previous approaches, improving our capacity to discriminate and quantify PBAP meta-classes. We evaluate the performance of several hierarchical agglomerative cluster analysis linkages and data normalisation methods using laboratory samples of known particle types and an ambient dataset. Fluorescent and non-fluorescent polystyrene latex spheres were sampled with a Wideband Integrated Bioaerosol Spectrometer (WIBS-4) where the optical size, asymmetry factor and fluorescent measurements were used as inputs to the analysis package. It was found that the Ward linkage with z-score or range normalisation performed best, correctly attributing 98 and 98.1 % of the data points respectively. The best performing methods were applied to the BEACHON-RoMBAS ambient dataset where it was found that the z-score and range normalisation methods yield similar results with each method producing clusters representative of fungal spores and bacterial aerosol, consistent with previous results. The z-score result was compared to clusters generated with previous approaches (WIBS AnalysiS Program, WASP) where we observe that the subsampling and comparative attribution method employed by WASP results in the overestimation of the fungal spore concentration by a factor of 1.5 and the underestimation of bacterial aerosol concentration by a factor of 5. We suggest that this likely due to errors arising from misatrribution due to poor centroid definition and failure to assign particles to a cluster as a result of the subsampling and comparative attribution method employed by WASP. The methods used here allow for the entire fluorescent population of particles to be analysed yielding an explict cluster attribution for each particle, improving cluster centroid definition and our capacity to discriminate and quantify PBAP meta-classes compared to previous approaches.

scholarly journals Control limit detection for source apportionment in Perlis River Basin, Malaysia

2017 ◽  
Vol 13 (3) ◽  
Author(s):  
Mohd Saiful Samsudin ◽  
Saiful Iskandar Khalit ◽  
Azman Azid ◽  
Hafizan Juahir ◽  
Ahmad Shakir Mohd Saudi ◽  
...  
Keyword(s):  
River Basin ◽  
Control Process ◽  
Principal Component ◽  
River Pollution ◽  
Quality Data ◽  
Water Quality Data ◽  
Data Set ◽  
Hierarchical Agglomerative Cluster ◽  
Limit Detection ◽  
Hierarchical Agglomerative Cluster Analysis

This study presents the application of selected environmetric in the Perlis River Basin. The results show PCA extracted nine principal components (PCs) with eigenvalues greater than one, which equates to about 77.15% of the total variance in the water-quality data set. The absolute principal component scores (APCS)-MLR model discovered BOD and COD as the main parameters, which indicates the measure of the agricultural pollution in the Perlis River Basin, the hierarchical agglomerative cluster analysis (HACA) shows 11 monitoring stations assembled into two clusters in accordance with similarities in the concentration of BOD and COD, which are grouped in P4. The X ̅ control chart shows that the mean concentration of BOD and COD in P4 is in the control process. The capability ratio (Cp) was applied to measure the risk of the concentration in terms of the river pollution in a subsequent period of time using the limit NWQS.

Sign in / Sign up

Export Citation Format

Share Document