Pub Date : 2020-07-15DOI: 10.1109/IISA50023.2020.9284382
Jazmine Mae Recario, Geoffrey A. Solano, Angelyn R. Lao
PlaPhy-SMD is a simple web application with a database management system that allows users to contribute data and provides them visualizations of the associations among plants, small-molecule drugs, human conditions and human genes in the form of tables and graphs. It aims to be of help in the field of phytomedicine since it does not only show researchers different natural sources for the development of new drugs and drug ingredients, but it also associates the natural sources, which are the plants, to the conditions and genes associated to the SMDs, which can be used as ingredients in developing new medicinal drugs, found in them. Also, it could serve as a pre-processing tool in evaluating the characteristics and application prospect of natural medicine. In addition to that, this is essential in discovering natural alternatives for synthetic medicine, since natural products are safer to use than the artificial ones.
{"title":"PlaPhy-SMD: A Database System of Plants and their Phytochemicals Integrated with Small-Molecule Drugs and their Condition and Gene Associations with Clustering and Product Ingredient Matching","authors":"Jazmine Mae Recario, Geoffrey A. Solano, Angelyn R. Lao","doi":"10.1109/IISA50023.2020.9284382","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284382","url":null,"abstract":"PlaPhy-SMD is a simple web application with a database management system that allows users to contribute data and provides them visualizations of the associations among plants, small-molecule drugs, human conditions and human genes in the form of tables and graphs. It aims to be of help in the field of phytomedicine since it does not only show researchers different natural sources for the development of new drugs and drug ingredients, but it also associates the natural sources, which are the plants, to the conditions and genes associated to the SMDs, which can be used as ingredients in developing new medicinal drugs, found in them. Also, it could serve as a pre-processing tool in evaluating the characteristics and application prospect of natural medicine. In addition to that, this is essential in discovering natural alternatives for synthetic medicine, since natural products are safer to use than the artificial ones.","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132042823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-15DOI: 10.1109/IISA50023.2020.9284355
Stavroula Tzima, Georgios D. Styliaras, Athanasios Bassounas
New technologies have changed the way we live, work, have fun and mobile phones are now one of the essential tools of work, communication and entertainment. Augmented Reality technology and the rapid spreading of mobile devices in everyday life are shaping new conditions in the culture field as well. Many studies focus on key questions of usability and technical issues without going into further analysis. In order to understand users/visitors needs and expectations as well as the role of technology in depth, the current study will try to answer an important question "what does impress users more, technology or content?". It is an important and a difficult question to be answered due to the diverse user’s profiles, the AR applications and sometimes the indistinct boundaries between the concepts of “like” and “impress”. The current research incorporates an AR app of cultural routes that could be found in every city/site and includes participants representing all ages and the associated categories (technology, theme, general) in order to approach the question in a balanced way. A qualitative research and results showed that more than the half select “both technology and content”, fewer users select only “content” and even less select only “technology”. Therefore, the AR technology continues to have a positive effect on users, content plays a significant key role but the way content and technology are combined emerges as the most important factor. Also, it is highlighted, that as users become more familiar with technology, they are becoming more demanding and more selective in using technology, making the creation of an AR app and generally the technology use more difficult to cover their increasing needs. In addition to, users’ view on the use of technology should not be ignored in order to avoid a negative attitude towards technology and more emphasis should be given on content and on applications that really have something innovative to add both to users and to cultural assets value.
{"title":"Augmented Reality applications in Cultural Heritage: Technology or Content?","authors":"Stavroula Tzima, Georgios D. Styliaras, Athanasios Bassounas","doi":"10.1109/IISA50023.2020.9284355","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284355","url":null,"abstract":"New technologies have changed the way we live, work, have fun and mobile phones are now one of the essential tools of work, communication and entertainment. Augmented Reality technology and the rapid spreading of mobile devices in everyday life are shaping new conditions in the culture field as well. Many studies focus on key questions of usability and technical issues without going into further analysis. In order to understand users/visitors needs and expectations as well as the role of technology in depth, the current study will try to answer an important question \"what does impress users more, technology or content?\". It is an important and a difficult question to be answered due to the diverse user’s profiles, the AR applications and sometimes the indistinct boundaries between the concepts of “like” and “impress”. The current research incorporates an AR app of cultural routes that could be found in every city/site and includes participants representing all ages and the associated categories (technology, theme, general) in order to approach the question in a balanced way. A qualitative research and results showed that more than the half select “both technology and content”, fewer users select only “content” and even less select only “technology”. Therefore, the AR technology continues to have a positive effect on users, content plays a significant key role but the way content and technology are combined emerges as the most important factor. Also, it is highlighted, that as users become more familiar with technology, they are becoming more demanding and more selective in using technology, making the creation of an AR app and generally the technology use more difficult to cover their increasing needs. In addition to, users’ view on the use of technology should not be ignored in order to avoid a negative attitude towards technology and more emphasis should be given on content and on applications that really have something innovative to add both to users and to cultural assets value.","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130395499","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-15DOI: 10.1109/IISA50023.2020.9284414
Eleni Alogogianni, M. Virvou
Undeclared work is, by definition, a multi-faceted phenomenon that needs to be detected. In welfare states, undeclared work results in loss of public revenue and thus resources critical for welfare mechanisms’ funding, lack of worker protection and, last but not least, unfair competition for legitimate businesses. Yet, little to no studies have proposed the use of sophisticated machine learning methods in tackling this severe socioeconomic problem. In this study, we demonstrate the application of an advanced data analysis method, the association rule mining, which has significant advantages over rule-based systems, in classifying employers likely to engage in undeclared work. Indeed, the results of this pilot project proved divulging, even to the most experienced labour inspectors, offering insights in patterns of employers’ illegal behaviour, that were previously unidentified.
{"title":"Association Rules and Machine Learning for Enhancing Undeclared Work Detection","authors":"Eleni Alogogianni, M. Virvou","doi":"10.1109/IISA50023.2020.9284414","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284414","url":null,"abstract":"Undeclared work is, by definition, a multi-faceted phenomenon that needs to be detected. In welfare states, undeclared work results in loss of public revenue and thus resources critical for welfare mechanisms’ funding, lack of worker protection and, last but not least, unfair competition for legitimate businesses. Yet, little to no studies have proposed the use of sophisticated machine learning methods in tackling this severe socioeconomic problem. In this study, we demonstrate the application of an advanced data analysis method, the association rule mining, which has significant advantages over rule-based systems, in classifying employers likely to engage in undeclared work. Indeed, the results of this pilot project proved divulging, even to the most experienced labour inspectors, offering insights in patterns of employers’ illegal behaviour, that were previously unidentified.","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121701798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-15DOI: 10.1109/IISA50023.2020.9284401
Avar Pentel, Lisanne-Liis Kaiva
All Estonia’s upper-secondary school students have three mandatory final state examinations – in mathematics, Estonian language and foreign language. We used data obtained from one school in order to predict student’s final examination scores based on previous grades and demographic data. Our aim was to find most important factors that contribute positively to final results and vice versa. Machine learning package Weka was used to build predictive models and with all tested attribute sets we got accuracy over 80% on classification. On continuous models we got mean absolute error close or less to 10, when range of test result was 0-100 points. Most of our attributes were subject grades on scale 1-5, and therefore, as we limited our testing sample with one school only, it gave interesting insights into how some subjects and teachers do contribute to final test results. And, surprisingly, it turned out, that for some test result, most significant predictor was negatively correlated to the result. It means that having bad grades in some subjects was a good predictor of success in final test. Besides being a useful tool for students who want to estimate possible test results beforehand, it is also a useful tool for measuring teachers’ contributions and relationships between different subjects.
{"title":"Predicting Students’ State Examination Results based on Previous Grades and Demographics","authors":"Avar Pentel, Lisanne-Liis Kaiva","doi":"10.1109/IISA50023.2020.9284401","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284401","url":null,"abstract":"All Estonia’s upper-secondary school students have three mandatory final state examinations – in mathematics, Estonian language and foreign language. We used data obtained from one school in order to predict student’s final examination scores based on previous grades and demographic data. Our aim was to find most important factors that contribute positively to final results and vice versa. Machine learning package Weka was used to build predictive models and with all tested attribute sets we got accuracy over 80% on classification. On continuous models we got mean absolute error close or less to 10, when range of test result was 0-100 points. Most of our attributes were subject grades on scale 1-5, and therefore, as we limited our testing sample with one school only, it gave interesting insights into how some subjects and teachers do contribute to final test results. And, surprisingly, it turned out, that for some test result, most significant predictor was negatively correlated to the result. It means that having bad grades in some subjects was a good predictor of success in final test. Besides being a useful tool for students who want to estimate possible test results beforehand, it is also a useful tool for measuring teachers’ contributions and relationships between different subjects.","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131134698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper we have reviewed the use of a cablebot system inside greenhouses and small plots for Precision Agriculture, that is able to inform the user for plant disease and micro-climate measurements. The proposed system moves alongside a cable above a crop and takes measurements by an array of sensors (relative humidity, temperature, air quality, spectral etc) that it carries.
{"title":"A Smart Cablebot for Spectral Imaging and Micro-climate measurements inside Greenhouses","authors":"Dionysios Bitas, Kyriakos Papastavros, Dimitris Tsipianitis","doi":"10.1109/IISA50023.2020.9284392","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284392","url":null,"abstract":"In this paper we have reviewed the use of a cablebot system inside greenhouses and small plots for Precision Agriculture, that is able to inform the user for plant disease and micro-climate measurements. The proposed system moves alongside a cable above a crop and takes measurements by an array of sensors (relative humidity, temperature, air quality, spectral etc) that it carries.","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131163289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-15DOI: 10.1109/IISA50023.2020.9284344
M. Lévano
The customization of students’ self-regulation regarding the use of information and communication technologies (ICT), is generally aimed as a process of dynamic transitions in their formative or non-formative process. The self-regulation process occurs in a context structured by the convergence theory (ICT and life environment). The objective of this work provides a framework for continuous improvement between the interrelation of activation of the use or adoption of ICT by students in a context of competencies. It was performed with a sample of students. An experimental random sampling design was used. The results demonstrate the manner of application of ICT used by the student in their self-learning. It is observed in the treatment of variability and uncertainty in the environment, it helps trainers to estimate times in training activities in an efficient and fat free way.
{"title":"Customization of self-regulation in the use of ICT for the learning process with continuous improvement: Catholic University of Temuco, Chile","authors":"M. Lévano","doi":"10.1109/IISA50023.2020.9284344","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284344","url":null,"abstract":"The customization of students’ self-regulation regarding the use of information and communication technologies (ICT), is generally aimed as a process of dynamic transitions in their formative or non-formative process. The self-regulation process occurs in a context structured by the convergence theory (ICT and life environment). The objective of this work provides a framework for continuous improvement between the interrelation of activation of the use or adoption of ICT by students in a context of competencies. It was performed with a sample of students. An experimental random sampling design was used. The results demonstrate the manner of application of ICT used by the student in their self-learning. It is observed in the treatment of variability and uncertainty in the environment, it helps trainers to estimate times in training activities in an efficient and fat free way.","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133346105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-15DOI: 10.1109/IISA50023.2020.9284368
Maria D. Karasimou, Vasileios Antonenas, Vasileios Laitsos, Vasileios Polychronides, L. Tsoukalas
Intelligent tools are brought to bear on the analysis of energy data from Greece in the period 2010-20. During this period a paradoxical phenomenon is observed namely, an increase in energy productivity in the midst of unprecedented economic decline as measured by Gross Domestic Product (GDP). Preliminary results identify improvements in the overall efficiency of capital due to the collapse in demand following draconian austerity measures. Background, directions and trends are analyzed, policy alternatives examined, and, a new measure of energy utilization with possible real-time applications is proposed.
{"title":"Intelligent Data Analytics from the Energy Economics of the Greek Debt Crisis","authors":"Maria D. Karasimou, Vasileios Antonenas, Vasileios Laitsos, Vasileios Polychronides, L. Tsoukalas","doi":"10.1109/IISA50023.2020.9284368","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284368","url":null,"abstract":"Intelligent tools are brought to bear on the analysis of energy data from Greece in the period 2010-20. During this period a paradoxical phenomenon is observed namely, an increase in energy productivity in the midst of unprecedented economic decline as measured by Gross Domestic Product (GDP). Preliminary results identify improvements in the overall efficiency of capital due to the collapse in demand following draconian austerity measures. Background, directions and trends are analyzed, policy alternatives examined, and, a new measure of energy utilization with possible real-time applications is proposed.","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130323902","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-15DOI: 10.1109/IISA50023.2020.9284403
A. Papapostolou, Filippos-Dimitrios K. Mexis, Elissaios Sarmas, C. Karakosta, J. Psarras
Energy Efficiency (EE) has been identified as one of the most cost-effective means aiming at reducing energy consumption while maintaining an equivalent level of economic activity. Mainstreaming EE financing is considered a key priority to avert climate change. The lack of evidence on the performance, commonly agreed procedures and standards for EE investments, particularly during the first stages of investment generation and pre-selection/pre-evaluation, are the key problems hampering EE investment financing. It is also true that often project developers do not have the expertise or resources to make a convincing financing case for investors. In order to boost EE investments, this paper proposes a Multi-Criteria Decision Analysis (MCDA) methodology intending to support financing institutions to identify attractive EE project ideas in the early development phase of project initiation and planning. The study implements the ELECTRE TRI method to benchmark EE project ideas in a standardized, investor recognizable credit rating form. A respective web-based tool facilitating the methodology and the screening of EE projects is also developed, supporting financing bodies and EE funds to rapidly detect and aggregate projects that meet the necessary criteria to be financed.
{"title":"Web-based Application for Screening Energy Efficiency Investments: A MCDA Approach","authors":"A. Papapostolou, Filippos-Dimitrios K. Mexis, Elissaios Sarmas, C. Karakosta, J. Psarras","doi":"10.1109/IISA50023.2020.9284403","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284403","url":null,"abstract":"Energy Efficiency (EE) has been identified as one of the most cost-effective means aiming at reducing energy consumption while maintaining an equivalent level of economic activity. Mainstreaming EE financing is considered a key priority to avert climate change. The lack of evidence on the performance, commonly agreed procedures and standards for EE investments, particularly during the first stages of investment generation and pre-selection/pre-evaluation, are the key problems hampering EE investment financing. It is also true that often project developers do not have the expertise or resources to make a convincing financing case for investors. In order to boost EE investments, this paper proposes a Multi-Criteria Decision Analysis (MCDA) methodology intending to support financing institutions to identify attractive EE project ideas in the early development phase of project initiation and planning. The study implements the ELECTRE TRI method to benchmark EE project ideas in a standardized, investor recognizable credit rating form. A respective web-based tool facilitating the methodology and the screening of EE projects is also developed, supporting financing bodies and EE funds to rapidly detect and aggregate projects that meet the necessary criteria to be financed.","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"18 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125619390","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-15DOI: 10.1109/IISA50023.2020.9284393
Evgenia Psarra, Ioannis Patiniotakis, Giannis Verginadis, Dimitris Apostolou, G. Mentzas
Data security in the healthcare domain is of paramount importance. There is a need for advanced access control mechanisms that can be used in the healthcare domain and raise security awareness. In this work, we report on the development of a web-based editor, that enables a user to edit concepts and properties for tailoring a context-aware security model for creating and enforcing access control policies for electronic health records (EHRs). These access control policies are to be enforced as part of two different sequential authorisation paradigms that will be employed for achieving high levels of security controls. These paradigms are the Attributebased Access Control (ABAC), which permits or denies access and/or grants or not editing rights to (encrypted) EHRs and the Attribute-based Encryption (ABE), which handles the way sensitive data should be decrypted, so as to edit functionalities for creating context-aware access policies (ABAC and ABE).
{"title":"Securing Access to Healthcare Data with Context-aware Policies","authors":"Evgenia Psarra, Ioannis Patiniotakis, Giannis Verginadis, Dimitris Apostolou, G. Mentzas","doi":"10.1109/IISA50023.2020.9284393","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284393","url":null,"abstract":"Data security in the healthcare domain is of paramount importance. There is a need for advanced access control mechanisms that can be used in the healthcare domain and raise security awareness. In this work, we report on the development of a web-based editor, that enables a user to edit concepts and properties for tailoring a context-aware security model for creating and enforcing access control policies for electronic health records (EHRs). These access control policies are to be enforced as part of two different sequential authorisation paradigms that will be employed for achieving high levels of security controls. These paradigms are the Attributebased Access Control (ABAC), which permits or denies access and/or grants or not editing rights to (encrypted) EHRs and the Attribute-based Encryption (ABE), which handles the way sensitive data should be decrypted, so as to edit functionalities for creating context-aware access policies (ABAC and ABE).","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131968864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-15DOI: 10.1109/IISA50023.2020.9284397
Agorakis Bompotas, A. Ilias, Maria Adamopoulos, Andreas Kanavos, C. Makris, G. Rompolas, A. Savvopoulos
Hotel customers express reviews for every accommodation service provided and/or for the accommodation as a whole. On the other hand, reviews are particularly interested for the tourism industry in order to extract customers’ opinions and aspects, which will assist them to improve their provided services. The reviews can be thoroughly found in the Web and their quantity can be considered as big data in Natural Language Processing. In this paper, we have designed an architecture and have implemented a system that initially utilizes some preprocessing techniques, as classic Natural Language Processing approaches, namely TF-IDF bag of words and word embeddings, are employed. These approaches can be further used as the input of various classifiers and Long Short Term Memory Neural Networks. The accuracy of these classifiers is evaluated on a dataset consisting of several reviews for the well known evaluation metrics, namely Precision, Recall and Fl-Measure.
{"title":"A Sentiment-based Hotel Review Summarization using LSTM Neural Networks","authors":"Agorakis Bompotas, A. Ilias, Maria Adamopoulos, Andreas Kanavos, C. Makris, G. Rompolas, A. Savvopoulos","doi":"10.1109/IISA50023.2020.9284397","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284397","url":null,"abstract":"Hotel customers express reviews for every accommodation service provided and/or for the accommodation as a whole. On the other hand, reviews are particularly interested for the tourism industry in order to extract customers’ opinions and aspects, which will assist them to improve their provided services. The reviews can be thoroughly found in the Web and their quantity can be considered as big data in Natural Language Processing. In this paper, we have designed an architecture and have implemented a system that initially utilizes some preprocessing techniques, as classic Natural Language Processing approaches, namely TF-IDF bag of words and word embeddings, are employed. These approaches can be further used as the input of various classifiers and Long Short Term Memory Neural Networks. The accuracy of these classifiers is evaluated on a dataset consisting of several reviews for the well known evaluation metrics, namely Precision, Recall and Fl-Measure.","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131877173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：