Mykolas Romeris University Institutional Repository
Not a member yet
8023 research outputs found
Sort by
Cultural Services of Natural Ecosystem in the Cities and Their Evaluation Methods
No full textCC BYClassification of ecosystem services emphasizing on cultural services and their significance for townspeople and
communities is discussed in the paper. The evaluation methods as well as aspects of monetary and non-monetary
evaluation of cultural services of natural ecosystems in the cities is analysed using relevant research methods. Empirical
research completed in four Lithuanian cities revealed the possibilities of harmonization of different research methods
for evaluation of cultural services of natural ecosystems
Towards Climate Sustainability of the Academic System in Europe and beyond
Full text linkCC BYThe urgency of the climate crisis is made abundantly
clear by the Sixth Assessment Report from the
Intergovernmental Panel on Climate Change (IPCC).
The academic system is making an important
positive impact by (i) research into the climate
crisis and its impact; (ii) research into mitigation
and adaptation strategies and technologies; (iii)
education of the general public as well as students;
(iv) science-based policy advice. In the present
report, we focus on the academic system’s negative
impact on the climate through its own operations.
As with essentially every sector of society, a
thorough transformation is necessary to achieve
climate sustainability. In the case of the academic
system, this need is accentuated by the following
point: academic institutions provide knowledge
on the climate crisis and potential solutions and
mitigation strategies, and therefore should also
act on that knowledge. In this way they can also
play a leading role in showing how a sector can
successfully transition to climate sustainability
Accuracy of Slovak Language Lemmatization and MSD Tagging – MorphoDiTa and SpaCy
Full text linkThe Slovak language, as a “typical” Slavic language, belongs to the group of moderately inflected languages, with three or four genders, two grammatical numbers, all
interacting with the inflections in somewhat complicated and unpredictable ways. The
inflections are realized primarily by suffixes, but with many irregularities; one suffix
encodes several relevant grammatical categories and the same suffix often reflects unrelated features in other words, a typical inflectional language not amenable to a heuristic
analysis. Following these limitations, lemmatization is often an indispensable step in
all kinds of text processing (starting with full-text search), and full morphosyntactic
analysis or description (MSD) is the core of corpus linguistic research. Given the core
importance of lemmatization and MSD in Slovak corpus linguistics, it is important to
realize its limitations and recognize achievable accuracy. Since modern approaches aim
to utilize deep learning and huge language models, we evaluate the accuracy of lemmatization + MSD in several common usage scenarios by comparing the state-of-the-art
“classical” lemmatizer and MSD tagger MorhoDiTa, based on perceptron; and spaCy,
using a multilingual BERT language model
Assessment of e-trade in global environment
Full text linkCC BY 4.0The article analyses the topic of e-trade assessment in a global environment. To achieve the objective, a detailed analysis of scientific works was carried out in order to identify the importance of e-trade assessment in a global
environment and, by removing the identified limitations, to develop a model of e-trade evaluation applicable to a global
environment. The empirical research was based on the developed e-trade evaluation model to test its effectiveness and
applicability in a global environment. Based on the data collected, a multi-criteria assessment of e-trade was carried
out, dividing the factors into five dimensions: emotional (consumer satisfaction and trust), technological (internet accessibility, data security and privacy), financial (e-GDP, e-trade sales, impact of e-trade on overall company turnover),
social (internet usage and purchasing volumes) and tax environment (VAT), and a comparative analysis of the countries to compare the results of economically similar countries, to find out why the market leaders are performing so
well in the e-trade sector, and to identify the methodologies and practices used in these countries, so as to identify the
most effective methods and practices that can be applied in other countries. The results of the multi-criteria assessment
al-lowed European countries to be classified into three groups: from market leaders to the most laggard countries. The
strongest growth rates are found in Ro-mania and Bulgaria. It is worth noting that e-trade is also unpopular in Southern European countries: Greece, Portugal, Spain, Italy, Malta, Cyprus
Using Machine Learning Models to Investigate Consumer Attitudes toward Online Behavioral Advertising
Full text linkCC BY-NC-ND 4.0The technique of online behavioral advertising (OBA) is a strategy that has been
widely used in the last decade by businesses and advertisers to deliver targeted advertising messages
to internet users. It is done by utilizing technology to record the habits of online shoppers, including
their searches and the content they visit. Users who browse the internet or use social media view
advertisements relevant to their interests, recent searches, and location. We study Twitter users’
attitudes about targeted ads using five different machine learning models in this research, applying
the CRISP-DM framework. Our primary focus is to develop a benchmark Twitter sentiment dataset
related to targeted ads and implement highly accurate machine learning algorithms to predict tweet
text sentiments when discussing targeted ads. The machine learning algorithms used are Logistic
Regression, Random Forest, Multinomial Naïve Bayes, Multi-Layer Perceptron, and Decision Tree.
We use accuracy, precision, recall, and the F1 measure to evaluate their performance. Logistic Regression using the content-based method provides the utmost accuracy of 0.88. We propose a model
that allows real-time consumer attitude research regarding retargeting ads. The results show that
logistic regression is the most accurate method for predicting customer responses to OBA campaigns
and that retargeting and OBA often cause negative feelings in consumers
Pirštų ir pėdų odos papiliarinių linijų raštų charakteristikos daktiloskopijos tyrimo kontekste
Full text linkThe material world is characterized by the interconnectioness and conditionality
of phenomena. Every crime affects various objects in the external
world and causes changes in the environment. In criminology, all these material
influences and changes are called “crime traces”. Since crime traces are
not homogeneous, they are investigated by several branches of forensic science
techniques. An important part of the trace investigation belongs to the field of
trassology. The trassology branch which studies the structure and properties of
the papillary ridge patterns and the use of its traces in evidence is called dactyloscopy.
When examining an object or a crime scene, investigators often find
fingerprints, sometimes palm prints, and less frequently barefoot prints, which
display papillary ridge patterns. The author hypothesizes that the papillary loop
and whorl ridge pattern on the corresponding toes and fingers of the same-sided
hand and foot pairs have statistically significant similarities.
If matching patterns are detected, the number of papillary lines from the
delta to the center of the same type of papillary patterns will be counted. This
process involves an examination of the general characteristics that are part of
the trace verification process when identifying a person. The general features
characterize both the external and internal features of the ridge pattern. The
lines in the center of the trace indicate the classification type, species, or special
category to which the trace belongs. This knowledge is important both for
crime scene investigators working at the scene of a crime and for experts in the
field conducting forensic examinations
From Knobhead to Sex Goddess: Swearwords in English Subtitles, Their Functions and Representation as Linguistic Linked Data
Full text linkPurpose: Swearwords represent an important social vehicle for human communication that, beyond mere insults, are conventionally used for expressing solidarity,
bonding, and banter, among other functions. Representing an empirically validated typology of such functions and annotated swearwords in subtitles as Linguistic Linked
Open Data (LLOD) provides a rich linguistic research platform for foul language. As a
first case study, we classify swearwords in the English subtitles of Bridget Jones’s Diary
into twelve unique functions and represent them with OntoLex-Lemon (Cimiano et al.,
2016)