Sabina Necula | Universitatea Alexandru Ioan Cuza Iasi (original) (raw)

Papers by Sabina Necula

Behavioral Sciences

In this study, we aim to investigate the influence of the time spent reading product information ... more In this study, we aim to investigate the influence of the time spent reading product information on consumer behavior in e-commerce. Given the rapid growth of e-commerce and the increasing importance of understanding online consumer behavior, our research focuses on gaining a deeper understanding of customer navigation on e-commerce websites and its effects on purchasing decisions. Recognizing the multidimensional and dynamic nature of consumer behavior, we utilize machine learning techniques, which offer the capacity to handle complex data structures and reveal hidden patterns within the data, thereby augmenting our comprehension of underlying consumer behavior mechanisms. By analyzing clickstream data using Machine Learning (ML) algorithms, we provide new insights into the internal structure of customer clusters and propose a methodology for analyzing non-linear relationships in datasets. Our results reveal that the time spent reading product-related information, combined with oth...

Electronics

Data science and machine learning are subjects largely debated in practice and in mainstream rese... more Data science and machine learning are subjects largely debated in practice and in mainstream research. Very often, they are overlapping due to their common purpose: prediction. Therefore, data science techniques mix with machine earning techniques in their mutual attempt to gain insights from data. Data contains multiple possible predictors, not necessarily structured, and it becomes difficult to extract insights. Identifying important or relevant features that can help improve the prediction power or to better characterize clusters of data is still debated in the scientific literature. This article uses diverse data science and machine learning techniques to identify the most relevant aspects which differentiate data science and machine learning. We used a publicly available dataset that describes multiple users who work in the field of data engineering. Among them, we selected data scientists and machine learning engineers and analyzed the resulting dataset. We designed the featur...

International Journal of Computers Communications & Control, 2014

This paper exploits different semantic web technologies and builds a prototype of semantic web ma... more This paper exploits different semantic web technologies and builds a prototype of semantic web mashup functionality based on an architecture proposed by us. The main scope is to improve decision-making processes. In this paper, we are focusing on querying different ontologies in order to improve decision-making semantic search. As a conclusion, we demonstrate that in order to improve decision-making semantic search there is a need of special constructions that a query language must support.

SSRN Electronic Journal, 2014

The use of many multimedia channels in order to bring information to target groups is not somethi... more The use of many multimedia channels in order to bring information to target groups is not something new. What is new is related to how these channels are exploited by mixing techniques and technologies. We realized an online questionnaire to identify the multimedia techniques/ tools that have impact on user's satisfaction. We used comparative statistical analyses (Levene's test) to observe if there are any significant differences between multimedia users and non-multimedia users. We identified that the preferred techniques are: the presence of a narrator, the existence of some suggestive images, slides and demos. These are only some factors that we identified. We studied also the influence of features as: access to, scenario type, interactivity, flexibility, additional options and effects and time dependency. We determined that the existence of useful links is an important factor for overall satisfaction of the user with multimedia materials.

Lecture Notes in Electrical Engineering, 2009

ABSTRACT

The International Journal of Digital Accounting Research, 2007

This paper surveys a selection of recent research results which use laboratory methods to contrib... more This paper surveys a selection of recent research results which use laboratory methods to contribute to our understanding of the accounting decisions' characteristics and of the accounting decision-making process. During accounting decision modelling process we observed that there are some qualitative factors which constraint the accounting decision-making and that this factors should be modelled by using the so called knowledge technologies. We present an example which treats the accounting decisions concerning fixed assets' management. We discussed the economic decisions, the accounting decisions, the knowledge required to make the accounting decisions related to fixed assets and the related models. The necessarily interactive role of theory development, laboratory experimentation and field observation is discussed.

Decisions’ modelling often relies on numbers and sy mbols and we might say that very often decisi... more Decisions’ modelling often relies on numbers and sy mbols and we might say that very often decision-makers interpret numbers in order to obtai n symbols that are qualitative factors. Interpretin g qualitative factors is an aspect that has little to d with rational approach of decision-making and in this way there are no static decision-models. We sus tain in this article that defining decision steps a nd information needed in making decisions belongs to t he decision-maker and in this respect the control on data sets must be specified by the decision-make r at the decisional place. In this scope, the aim of this research is to ident ify the way of making business decisions. The results discuss the optimal way of using different t chnologies.

The current paper aims to study Web ontologies from a semiotic perspective. On the one hand, the ... more The current paper aims to study Web ontologies from a semiotic perspective. On the one hand, the study of signs is constantly used lately in the analysis of the social life, of organisations and informational systems. On the other hand, Web ontologies may be seen as systems of signs, wishing to catch the reality of a certain field by identifying fundamental categories of identities and the relations between them. Their intention is to describe their significance as accurately as possible, so as to ensure the best communication between computing systems. Since any act of communication includes and involves signs and codes (Fiske, J., quoted in Borţun, 2006), in the current paper we bring to discussion the opportunity of using semiotics, as the science that studies signs, in the study of the Web ontologies.

This paper presents with examples some queries made on data sets using SPARQL. We treat the probl... more This paper presents with examples some queries made on data sets using SPARQL. We treat the problem of available standards and tools. We show data tests resulted from querying different ontologies. Also the article treats the problem of describing data by using Resource Description Format.

This paper treats with examples the practical use of Semantic Web technologies for describing bus... more This paper treats with examples the practical use of Semantic Web technologies for describing business data. The main problems that the present paper addresses are related to identifying the main activities/ functions of an organization that can be represented with Semantic Web technologies. We treat in the beginning of the paper the main functions of an organization that can be addressed with Semantic Web technologies. We continue by presenting the main technological aspects involved in developing Semantic Web applications in order to publish semantic web data. We present some examples and then we discuss our main ideas. The paper ends with some conclusions.

The specialty studies have sought to emphasize the importance of IT tools in human reasoning emul... more The specialty studies have sought to emphasize the importance of IT tools in human reasoning emulation, in developing methods and techniques in order to extract knowledge based on text, or in developing methods in order to improve decision-making process. This paper tries to present the functionalities required by decision support systems in order to sustain the business processes.

This paper tries to discuss some findings in mathematical decision-making modeling models with ap... more This paper tries to discuss some findings in mathematical decision-making modeling models with applications in business processes. We start by presenting some technological implications and implementations of decision-making models. After this we discuss some implementations realized by us and that consists in a neural network, a JAVA implementation of the decision-making model, an expert systems-shell implementation and an implementation with ontology and inference engine. The paper ends with usefull conclusions drawn for decisionmaking modeling activities. Key-Words: decision-making, DSS, KBS, ontology, inference engine, OWL

The usability of financial software has always been a main problem for software producers and it ... more The usability of financial software has always been a main problem for software producers and it was always been related to the users’ degree of acceptability. In this article we started from the main premise that knowledge of making financial decisions is local, depends on context and we try to define architecture suitable in developing financial software.

This paper tries to identify some methodological consideration in building business ontologies fo... more This paper tries to identify some methodological consideration in building business ontologies for decision support. We treat the problems that business domain poses for knowledge engineers. We also discuss the main semantic web technologies involved in developing ontologies. We consider also the problems that decision support presents for ontologies. From these considerations we identify and discuss some methodological aspects that building ontologies for business decision support must take into considerations.

Decisions’ modelling often relies on numbers and symbols and we might say that very often decisio... more Decisions’ modelling often relies on numbers and symbols and we might say that very often decision-makers interpret numbers in order to obtain symbols that are qualitative factors. Interpreting qualitative factors is an aspect that has little to do with rational approach of decision-making and in this way there are no static decision-models. We sustain in this article that defining decision steps and information needed in making decisions belongs to the decision-maker and in this respect the control on data sets must be specified by the decision-maker at the decisional place. In this scope, the aim of this research is to identify the way of making business decisions. The results discuss the optimal way of using different technologies.

The present paper treats an important aspect which concerns semantic web databases. Our research ... more The present paper treats an important aspect which concerns semantic web databases. Our research motivation is given by the problems that semantic web databases raise for the quality characteristic. We try to identify which are the main criteria to take into consideration when building a semantic web database. The research methodology consists in approaching the current literature, discussing the main practical aspects resulted from tests and analysis and treating the problem of quality in respect with a number of characteristics related to the semantic model. The main findings and implications are in the area of testing this quality. We start the paper with an introduction, we continue by presenting the research design, we discuss the semantic model, the main characteristics of a semantic web database in terms of quality and testing.

Nowadays Decision Support Systems deal with impressive amount of information. Current Decision Su... more Nowadays Decision Support Systems deal with impressive amount of information. Current Decision Support Systems are customized solutions, possible to be used only in the context for which they were developed. In addition to this the information integration is other common problem of the Decision Support Systems. This paper tries to outline the main idea that in order that Decision Support Systems users' to be satisfied with the solution provided two conditions must be assured: the possibility to apply knowledge at the decision moment and place by the decision makers and the semantic integration of information. In this work we analyze the direct influence of the two conditions enunciated above and we came with a solution that is based on ontology, Semantic Web technologies and inference engine. We demonstrate the contribution of our approach by undertaking three scenarios from business decision making processes.

This study focuses on the problem of absorbing the researches and outcomes of innovation processe... more This study focuses on the problem of absorbing the researches and outcomes of innovation processes into the economy. Our objective was to address this problem by identifying the main factors that are related with state’s support on innovation processes through public policies. Our approach took into consideration the case of Romania because our study is concentrated on identifying factors in order to discuss later solutions. We used public data available from the National Institute of Statistics, the National Council of Scientific Research, and from the National Authority for Scientific Research. Our results show that the efficiency of absorption consists in the right balance between researches diversity and researches specialization. We also found that state’s public policies influence the respective balance. The implications that our study identified show that the efficiency of research and development public policies relates to participants’ integrity and state’s leadership. The ...

The paper tries to identify some causes and implications of the web phenomena into the decision m... more The paper tries to identify some causes and implications of the web phenomena into the decision making field. It also includes examples in order to better justify the ideas. The literature and the practice are very rich in examples of Decision Support Systems (DSS) and Business Intelligence products but they are rather considered complex applications made to interact over the internet but not entirely running within the Internet. In order to arrive to this title we have also tested a few on-line products starting with simple office tools (Google docs – spreadsheets) or more specialized ones (Nesstar - analytics). And why this counts in this article? - Partially because when thinking of solvers and trend charts a spreadsheet may be considered a basic form of DSS. The main question is whether or not the on-line applications developers implement such functionalities in their products. Beyond the practical approach and the obvious criticism, the main idea of the paper is to make us real...

Behavioral Sciences

In this study, we aim to investigate the influence of the time spent reading product information ... more In this study, we aim to investigate the influence of the time spent reading product information on consumer behavior in e-commerce. Given the rapid growth of e-commerce and the increasing importance of understanding online consumer behavior, our research focuses on gaining a deeper understanding of customer navigation on e-commerce websites and its effects on purchasing decisions. Recognizing the multidimensional and dynamic nature of consumer behavior, we utilize machine learning techniques, which offer the capacity to handle complex data structures and reveal hidden patterns within the data, thereby augmenting our comprehension of underlying consumer behavior mechanisms. By analyzing clickstream data using Machine Learning (ML) algorithms, we provide new insights into the internal structure of customer clusters and propose a methodology for analyzing non-linear relationships in datasets. Our results reveal that the time spent reading product-related information, combined with oth...

Electronics

Data science and machine learning are subjects largely debated in practice and in mainstream rese... more Data science and machine learning are subjects largely debated in practice and in mainstream research. Very often, they are overlapping due to their common purpose: prediction. Therefore, data science techniques mix with machine earning techniques in their mutual attempt to gain insights from data. Data contains multiple possible predictors, not necessarily structured, and it becomes difficult to extract insights. Identifying important or relevant features that can help improve the prediction power or to better characterize clusters of data is still debated in the scientific literature. This article uses diverse data science and machine learning techniques to identify the most relevant aspects which differentiate data science and machine learning. We used a publicly available dataset that describes multiple users who work in the field of data engineering. Among them, we selected data scientists and machine learning engineers and analyzed the resulting dataset. We designed the featur...

International Journal of Computers Communications & Control, 2014

This paper exploits different semantic web technologies and builds a prototype of semantic web ma... more This paper exploits different semantic web technologies and builds a prototype of semantic web mashup functionality based on an architecture proposed by us. The main scope is to improve decision-making processes. In this paper, we are focusing on querying different ontologies in order to improve decision-making semantic search. As a conclusion, we demonstrate that in order to improve decision-making semantic search there is a need of special constructions that a query language must support.

SSRN Electronic Journal, 2014

The use of many multimedia channels in order to bring information to target groups is not somethi... more The use of many multimedia channels in order to bring information to target groups is not something new. What is new is related to how these channels are exploited by mixing techniques and technologies. We realized an online questionnaire to identify the multimedia techniques/ tools that have impact on user's satisfaction. We used comparative statistical analyses (Levene's test) to observe if there are any significant differences between multimedia users and non-multimedia users. We identified that the preferred techniques are: the presence of a narrator, the existence of some suggestive images, slides and demos. These are only some factors that we identified. We studied also the influence of features as: access to, scenario type, interactivity, flexibility, additional options and effects and time dependency. We determined that the existence of useful links is an important factor for overall satisfaction of the user with multimedia materials.

Lecture Notes in Electrical Engineering, 2009

ABSTRACT

The International Journal of Digital Accounting Research, 2007

This paper surveys a selection of recent research results which use laboratory methods to contrib... more This paper surveys a selection of recent research results which use laboratory methods to contribute to our understanding of the accounting decisions' characteristics and of the accounting decision-making process. During accounting decision modelling process we observed that there are some qualitative factors which constraint the accounting decision-making and that this factors should be modelled by using the so called knowledge technologies. We present an example which treats the accounting decisions concerning fixed assets' management. We discussed the economic decisions, the accounting decisions, the knowledge required to make the accounting decisions related to fixed assets and the related models. The necessarily interactive role of theory development, laboratory experimentation and field observation is discussed.

Decisions’ modelling often relies on numbers and sy mbols and we might say that very often decisi... more Decisions’ modelling often relies on numbers and sy mbols and we might say that very often decision-makers interpret numbers in order to obtai n symbols that are qualitative factors. Interpretin g qualitative factors is an aspect that has little to d with rational approach of decision-making and in this way there are no static decision-models. We sus tain in this article that defining decision steps a nd information needed in making decisions belongs to t he decision-maker and in this respect the control on data sets must be specified by the decision-make r at the decisional place. In this scope, the aim of this research is to ident ify the way of making business decisions. The results discuss the optimal way of using different t chnologies.

The current paper aims to study Web ontologies from a semiotic perspective. On the one hand, the ... more The current paper aims to study Web ontologies from a semiotic perspective. On the one hand, the study of signs is constantly used lately in the analysis of the social life, of organisations and informational systems. On the other hand, Web ontologies may be seen as systems of signs, wishing to catch the reality of a certain field by identifying fundamental categories of identities and the relations between them. Their intention is to describe their significance as accurately as possible, so as to ensure the best communication between computing systems. Since any act of communication includes and involves signs and codes (Fiske, J., quoted in Borţun, 2006), in the current paper we bring to discussion the opportunity of using semiotics, as the science that studies signs, in the study of the Web ontologies.

This paper presents with examples some queries made on data sets using SPARQL. We treat the probl... more This paper presents with examples some queries made on data sets using SPARQL. We treat the problem of available standards and tools. We show data tests resulted from querying different ontologies. Also the article treats the problem of describing data by using Resource Description Format.

This paper treats with examples the practical use of Semantic Web technologies for describing bus... more This paper treats with examples the practical use of Semantic Web technologies for describing business data. The main problems that the present paper addresses are related to identifying the main activities/ functions of an organization that can be represented with Semantic Web technologies. We treat in the beginning of the paper the main functions of an organization that can be addressed with Semantic Web technologies. We continue by presenting the main technological aspects involved in developing Semantic Web applications in order to publish semantic web data. We present some examples and then we discuss our main ideas. The paper ends with some conclusions.

The specialty studies have sought to emphasize the importance of IT tools in human reasoning emul... more The specialty studies have sought to emphasize the importance of IT tools in human reasoning emulation, in developing methods and techniques in order to extract knowledge based on text, or in developing methods in order to improve decision-making process. This paper tries to present the functionalities required by decision support systems in order to sustain the business processes.

This paper tries to discuss some findings in mathematical decision-making modeling models with ap... more This paper tries to discuss some findings in mathematical decision-making modeling models with applications in business processes. We start by presenting some technological implications and implementations of decision-making models. After this we discuss some implementations realized by us and that consists in a neural network, a JAVA implementation of the decision-making model, an expert systems-shell implementation and an implementation with ontology and inference engine. The paper ends with usefull conclusions drawn for decisionmaking modeling activities. Key-Words: decision-making, DSS, KBS, ontology, inference engine, OWL

The usability of financial software has always been a main problem for software producers and it ... more The usability of financial software has always been a main problem for software producers and it was always been related to the users’ degree of acceptability. In this article we started from the main premise that knowledge of making financial decisions is local, depends on context and we try to define architecture suitable in developing financial software.

This paper tries to identify some methodological consideration in building business ontologies fo... more This paper tries to identify some methodological consideration in building business ontologies for decision support. We treat the problems that business domain poses for knowledge engineers. We also discuss the main semantic web technologies involved in developing ontologies. We consider also the problems that decision support presents for ontologies. From these considerations we identify and discuss some methodological aspects that building ontologies for business decision support must take into considerations.

Decisions’ modelling often relies on numbers and symbols and we might say that very often decisio... more Decisions’ modelling often relies on numbers and symbols and we might say that very often decision-makers interpret numbers in order to obtain symbols that are qualitative factors. Interpreting qualitative factors is an aspect that has little to do with rational approach of decision-making and in this way there are no static decision-models. We sustain in this article that defining decision steps and information needed in making decisions belongs to the decision-maker and in this respect the control on data sets must be specified by the decision-maker at the decisional place. In this scope, the aim of this research is to identify the way of making business decisions. The results discuss the optimal way of using different technologies.

The present paper treats an important aspect which concerns semantic web databases. Our research ... more The present paper treats an important aspect which concerns semantic web databases. Our research motivation is given by the problems that semantic web databases raise for the quality characteristic. We try to identify which are the main criteria to take into consideration when building a semantic web database. The research methodology consists in approaching the current literature, discussing the main practical aspects resulted from tests and analysis and treating the problem of quality in respect with a number of characteristics related to the semantic model. The main findings and implications are in the area of testing this quality. We start the paper with an introduction, we continue by presenting the research design, we discuss the semantic model, the main characteristics of a semantic web database in terms of quality and testing.

Nowadays Decision Support Systems deal with impressive amount of information. Current Decision Su... more Nowadays Decision Support Systems deal with impressive amount of information. Current Decision Support Systems are customized solutions, possible to be used only in the context for which they were developed. In addition to this the information integration is other common problem of the Decision Support Systems. This paper tries to outline the main idea that in order that Decision Support Systems users' to be satisfied with the solution provided two conditions must be assured: the possibility to apply knowledge at the decision moment and place by the decision makers and the semantic integration of information. In this work we analyze the direct influence of the two conditions enunciated above and we came with a solution that is based on ontology, Semantic Web technologies and inference engine. We demonstrate the contribution of our approach by undertaking three scenarios from business decision making processes.

This study focuses on the problem of absorbing the researches and outcomes of innovation processe... more This study focuses on the problem of absorbing the researches and outcomes of innovation processes into the economy. Our objective was to address this problem by identifying the main factors that are related with state’s support on innovation processes through public policies. Our approach took into consideration the case of Romania because our study is concentrated on identifying factors in order to discuss later solutions. We used public data available from the National Institute of Statistics, the National Council of Scientific Research, and from the National Authority for Scientific Research. Our results show that the efficiency of absorption consists in the right balance between researches diversity and researches specialization. We also found that state’s public policies influence the respective balance. The implications that our study identified show that the efficiency of research and development public policies relates to participants’ integrity and state’s leadership. The ...

The paper tries to identify some causes and implications of the web phenomena into the decision m... more The paper tries to identify some causes and implications of the web phenomena into the decision making field. It also includes examples in order to better justify the ideas. The literature and the practice are very rich in examples of Decision Support Systems (DSS) and Business Intelligence products but they are rather considered complex applications made to interact over the internet but not entirely running within the Internet. In order to arrive to this title we have also tested a few on-line products starting with simple office tools (Google docs – spreadsheets) or more specialized ones (Nesstar - analytics). And why this counts in this article? - Partially because when thinking of solvers and trend charts a spreadsheet may be considered a basic form of DSS. The main question is whether or not the on-line applications developers implement such functionalities in their products. Beyond the practical approach and the obvious criticism, the main idea of the paper is to make us real...