Summarization is an integral part of modern Internet. In social networks, which have become primary information sources, users have grown accustomed to condense their writing. Content providers routinely publish short textual excerpts to these platforms as well. However, with larger quantities of small documents becoming constantly available, search engines now have less data to index, classify and retrieve relevant information. In this regard, more research is needed to show how reliable the current Information Retrieval (IR) algorithms are when confronted to collections of exclusively short documents, such as the ones arising from social media.This paper explores the semantic proximity between human summaries and queries through cluster analysis, and how it relates to IR. Roughly, the k-means algorithm was used to cluster two collections of summaries by their semantic similarity: one in English and one in Spanish. This, to measure how summarization may affect information content in cluster-based IR. Furthermore, the same algorithm was used to measure how documents grouped around a set of artificially generated queries.The results show that, regardless of the language, providing the algorithm with previous category knowledge may contribute to increase the accuracy of cluster-based document classification. Furthermore, some evidences points to the effect of summary quality in retrievability: summaries created by specialized summarizers induced more distinguishable clusters than summaries created by university students. Future work in this area may serve to adapt existing algorithms to big collections of short documents, improving IR performance in cases where machine learning techniques are not available.
{"title":"Measuring the Effects of Summarization in Cluster-based Information Retrieval","authors":"Arturo Curiel, Claudio Gutiérrez-Soto, Pablo-Nicolas Soto-Borquez, Patricio Galdames","doi":"10.1109/SCCC51225.2020.9281189","DOIUrl":"https://doi.org/10.1109/SCCC51225.2020.9281189","url":null,"abstract":"Summarization is an integral part of modern Internet. In social networks, which have become primary information sources, users have grown accustomed to condense their writing. Content providers routinely publish short textual excerpts to these platforms as well. However, with larger quantities of small documents becoming constantly available, search engines now have less data to index, classify and retrieve relevant information. In this regard, more research is needed to show how reliable the current Information Retrieval (IR) algorithms are when confronted to collections of exclusively short documents, such as the ones arising from social media.This paper explores the semantic proximity between human summaries and queries through cluster analysis, and how it relates to IR. Roughly, the k-means algorithm was used to cluster two collections of summaries by their semantic similarity: one in English and one in Spanish. This, to measure how summarization may affect information content in cluster-based IR. Furthermore, the same algorithm was used to measure how documents grouped around a set of artificially generated queries.The results show that, regardless of the language, providing the algorithm with previous category knowledge may contribute to increase the accuracy of cluster-based document classification. Furthermore, some evidences points to the effect of summary quality in retrievability: summaries created by specialized summarizers induced more distinguishable clusters than summaries created by university students. Future work in this area may serve to adapt existing algorithms to big collections of short documents, improving IR performance in cases where machine learning techniques are not available.","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133758203","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 : 2020-11-16DOI: 10.1109/SCCC51225.2020.9281166
Manuel A. Lavado, O. Herrera, A. Mellado
The teaching and learning process is still complex in the engineering area. Traditionally there are imperative courses with a high failure rate because of their complicated topics. This work presents a model of learning support with two fundamental aspects: technological support and peer learning. First, the technological platform is a multi-tooled social network. On the other hand, peer learning includes collaboration, bonding, feedback, and autonomous learning, as fundamental aspects of its implementation. Another crucial element of this model is the active participation of the assistants, who are the peers trained to guide the students in the process. This mentoring takes place in two environments, face-to-face and virtual. The face-to-face environment gathers all the infrastructure and human resources of the Colegio de Ayudantes (institutional unit), while the virtual environment contemplates the social network along with a set of tools that support this model. There are initial results of validation of the platform regarding its use and potential. Although this implementation starts in imperative courses of the faculty, it can be easily expanded to other courses of the university. This implementation can be possible due to the unique characteristics of a social network that self-regulates its growth.
{"title":"Peer learning supported on a social network. A strategy for critical courses in engineering","authors":"Manuel A. Lavado, O. Herrera, A. Mellado","doi":"10.1109/SCCC51225.2020.9281166","DOIUrl":"https://doi.org/10.1109/SCCC51225.2020.9281166","url":null,"abstract":"The teaching and learning process is still complex in the engineering area. Traditionally there are imperative courses with a high failure rate because of their complicated topics. This work presents a model of learning support with two fundamental aspects: technological support and peer learning. First, the technological platform is a multi-tooled social network. On the other hand, peer learning includes collaboration, bonding, feedback, and autonomous learning, as fundamental aspects of its implementation. Another crucial element of this model is the active participation of the assistants, who are the peers trained to guide the students in the process. This mentoring takes place in two environments, face-to-face and virtual. The face-to-face environment gathers all the infrastructure and human resources of the Colegio de Ayudantes (institutional unit), while the virtual environment contemplates the social network along with a set of tools that support this model. There are initial results of validation of the platform regarding its use and potential. Although this implementation starts in imperative courses of the faculty, it can be easily expanded to other courses of the university. This implementation can be possible due to the unique characteristics of a social network that self-regulates its growth.","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"219 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131460390","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 : 2020-11-16DOI: 10.1109/SCCC51225.2020.9281190
V. A. Sánchez, Luz Chourio-Acevedo, Jacqueline Köhler Casasempere, G. Muñoz
Student attrition is a long-lasting problem which affects higher education institutions around the world. In the Chilean context, this phenomenon needs to be addressed, as it is considered for university accreditation and undergraduate education quality assessment. The rather high drop-out rate of first-year students at the Departamento de Ingeniería Informatica of Universidad de Santiago de Chile has led to the creation of Ca-chor@404, a peer-instruction based accompaniment programme which supports incoming students by providing tutorials on key subjects and assisting them in their adaptation to university life. To succeed, the programme is led by a multidisciplinary team and considers different aspects of first-year student needs. The current Covid-19 pandemic, with its associated quarantine, has redefined some key aspects of university life adaptation, thus forcing Cachorr@404 to adjust to the new context. The adaptation process has turned into a learning experience regarding the use of new technologies to support the teaching-learning process within the programme’s initial courses. This article attempts to describe this accompaniment programme, emphasising key issues that emerged from the global contingency.
{"title":"Cachorr@404: Peer-instruction practices during quarantine times","authors":"V. A. Sánchez, Luz Chourio-Acevedo, Jacqueline Köhler Casasempere, G. Muñoz","doi":"10.1109/SCCC51225.2020.9281190","DOIUrl":"https://doi.org/10.1109/SCCC51225.2020.9281190","url":null,"abstract":"Student attrition is a long-lasting problem which affects higher education institutions around the world. In the Chilean context, this phenomenon needs to be addressed, as it is considered for university accreditation and undergraduate education quality assessment. The rather high drop-out rate of first-year students at the Departamento de Ingeniería Informatica of Universidad de Santiago de Chile has led to the creation of Ca-chor@404, a peer-instruction based accompaniment programme which supports incoming students by providing tutorials on key subjects and assisting them in their adaptation to university life. To succeed, the programme is led by a multidisciplinary team and considers different aspects of first-year student needs. The current Covid-19 pandemic, with its associated quarantine, has redefined some key aspects of university life adaptation, thus forcing Cachorr@404 to adjust to the new context. The adaptation process has turned into a learning experience regarding the use of new technologies to support the teaching-learning process within the programme’s initial courses. This article attempts to describe this accompaniment programme, emphasising key issues that emerged from the global contingency.","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134532357","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 : 2020-11-16DOI: 10.1109/SCCC51225.2020.9281172
Norka Bedregal-Alpaca, Víctor Manuel Cornejo Aparicio, Olha Sharhorodska
The low presence of women in engineering careers is a problem in Peru, a country characterized by marked social and economic differences and an educational system with low levels of performance, high desertion and low terminal efficiency. In the specialty of Systems Engineering of a public university, the low female presence in two dimensions is analyzed: income and academic performance. In both cases, performance rates are worked.The results reveal that college admission patterns are similar for both sexes. Academic performance indicators show differences and indicate that women tend to be more efficient. In the areas of Programming and Mathematics, most students face difficulties, however, in both cases women perform better. In general training subjects, women are geared towards further developing soft skills.Some conclusions are set out as a starting point for educational actions to improve women's income and performance rates and to improve female retention and graduation rates.
{"title":"Academic performance and gender in the first year of Systems Engineering","authors":"Norka Bedregal-Alpaca, Víctor Manuel Cornejo Aparicio, Olha Sharhorodska","doi":"10.1109/SCCC51225.2020.9281172","DOIUrl":"https://doi.org/10.1109/SCCC51225.2020.9281172","url":null,"abstract":"The low presence of women in engineering careers is a problem in Peru, a country characterized by marked social and economic differences and an educational system with low levels of performance, high desertion and low terminal efficiency. In the specialty of Systems Engineering of a public university, the low female presence in two dimensions is analyzed: income and academic performance. In both cases, performance rates are worked.The results reveal that college admission patterns are similar for both sexes. Academic performance indicators show differences and indicate that women tend to be more efficient. In the areas of Programming and Mathematics, most students face difficulties, however, in both cases women perform better. In general training subjects, women are geared towards further developing soft skills.Some conclusions are set out as a starting point for educational actions to improve women's income and performance rates and to improve female retention and graduation rates.","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134158931","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 : 2020-11-16DOI: 10.1109/SCCC51225.2020.9281177
F. J. Díaz, Noelia Soledad Gómez, Magali Catino
This work is the result of an investigation carried out within the framework of a research grant. The work experience that this team carried out was aimed at describing and systematizing the configuration of computational thinking, its incidence and validity in the educational field from the analysis of public policies, from an interdisciplinary approach. The experience carried out was developed based on a bibliographic and documentary analysis work, which allowed recovering the concept of computational thinking to analyze it in conjunction with the development of critical pedagogical practice and the concept of competences. Here an analysis of some of the current debates presented by computational thinking and its teaching is presented in order to promote a line of dialogue and problematization between what was done, is done and is projected on this subject.
{"title":"Analysis on the incorporation of technologies with a pedagogical perspective","authors":"F. J. Díaz, Noelia Soledad Gómez, Magali Catino","doi":"10.1109/SCCC51225.2020.9281177","DOIUrl":"https://doi.org/10.1109/SCCC51225.2020.9281177","url":null,"abstract":"This work is the result of an investigation carried out within the framework of a research grant. The work experience that this team carried out was aimed at describing and systematizing the configuration of computational thinking, its incidence and validity in the educational field from the analysis of public policies, from an interdisciplinary approach. The experience carried out was developed based on a bibliographic and documentary analysis work, which allowed recovering the concept of computational thinking to analyze it in conjunction with the development of critical pedagogical practice and the concept of competences. Here an analysis of some of the current debates presented by computational thinking and its teaching is presented in order to promote a line of dialogue and problematization between what was done, is done and is projected on this subject.","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131159265","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 : 2020-11-16DOI: 10.1109/SCCC51225.2020.9281270
A. Garcia, S. Casas
Mobile devices are the main Internet access means today. Smartphones’ capabilities added to the growth of wireless networks, enable millions of people to take advantage of resources, contents and applications for different purposes on a daily basis. A degraded performance can be produced by different factors and users can undergo unsatisfactory experiences. Therefore, Quality of Experience (QoE) is a research topic of wide interest, which provides methods to analyze the general acceptability of an application or service, as subjectively perceived by the end user. This perception can be influenced by users’ expectations and their context. The QoE can be analyzed through subjective metrics obtained from questionnaires and/or surveys and/or objective metrics calculated automatically from the device’s properties and Quality of Service (QoS). This work presents the findings of an unsupervised field study conducted over 17 days in the city Río Gallegos, Argentina, to explore mobile QoE. Furthermore, the correspondence between the objective observations and the users’ opinions were analyzed to identify contextual conditions that can influence the obtained results. For this reason, the CovidInfo application was developed and publicly shared. Using their own mobile devices in everyday context, 31 users interacted with the CovidInfo application, recording values for eight objective metrics and users’ opinion. The total data set collected consisted of 16990 records. The analysis of the CovidInfo application yielded positive results, while 89% of the registered values corresponded to a good QoE. This allowed establishing a relationship between the values recorded for the objective metrics and those of the users’ opinion, both of which showed good values (88% and 97%, respectively).
{"title":"Mobile QoE exploration: an unsupervised field study in an Argentine Patagonian city","authors":"A. Garcia, S. Casas","doi":"10.1109/SCCC51225.2020.9281270","DOIUrl":"https://doi.org/10.1109/SCCC51225.2020.9281270","url":null,"abstract":"Mobile devices are the main Internet access means today. Smartphones’ capabilities added to the growth of wireless networks, enable millions of people to take advantage of resources, contents and applications for different purposes on a daily basis. A degraded performance can be produced by different factors and users can undergo unsatisfactory experiences. Therefore, Quality of Experience (QoE) is a research topic of wide interest, which provides methods to analyze the general acceptability of an application or service, as subjectively perceived by the end user. This perception can be influenced by users’ expectations and their context. The QoE can be analyzed through subjective metrics obtained from questionnaires and/or surveys and/or objective metrics calculated automatically from the device’s properties and Quality of Service (QoS). This work presents the findings of an unsupervised field study conducted over 17 days in the city Río Gallegos, Argentina, to explore mobile QoE. Furthermore, the correspondence between the objective observations and the users’ opinions were analyzed to identify contextual conditions that can influence the obtained results. For this reason, the CovidInfo application was developed and publicly shared. Using their own mobile devices in everyday context, 31 users interacted with the CovidInfo application, recording values for eight objective metrics and users’ opinion. The total data set collected consisted of 16990 records. The analysis of the CovidInfo application yielded positive results, while 89% of the registered values corresponded to a good QoE. This allowed establishing a relationship between the values recorded for the objective metrics and those of the users’ opinion, both of which showed good values (88% and 97%, respectively).","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125180349","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 : 2020-11-16DOI: 10.1109/SCCC51225.2020.9281191
Giovanni Giachetti, Beatriz Marín, J. Vara
Assessing and certifying the functional safety of the software of critical systems is of paramount importance, since any failure might produce significant costs as well as harm to people. Some common examples of critical systems are transport vehicles (trains, airplanes, cars…), medical devices, and critical infrastructures (nuclear plants, oil platforms…). Safety certification intends to reduce the risk of failure to an acceptable level in compliance with standards. IEC 61508 is a reference safety standard whose use is specialized in some domains, such ISO 26262 for automotive and EN 50128 for railway. For applying these standards, the use of Model-Driven approaches based on UML Profiles is a suitable alternative. However, UML profiles are usually manually defined, which is a highly time-consuming task and error-prone. In addition, manually defined UML profiles are difficult to validate in relation to the reference standards and to the coverage of safety concepts. This paper presents the adaptation of an existing approach for automatic UML Profile generation to support the generation of UML Profiles for safety specifications that are based on IEC 61508. As a result, it is possible to reduce the time and errors that are common in a manual specification of safety UML Profiles.
{"title":"Automatic Generation of UML Profiles for Representing Safety Standards","authors":"Giovanni Giachetti, Beatriz Marín, J. Vara","doi":"10.1109/SCCC51225.2020.9281191","DOIUrl":"https://doi.org/10.1109/SCCC51225.2020.9281191","url":null,"abstract":"Assessing and certifying the functional safety of the software of critical systems is of paramount importance, since any failure might produce significant costs as well as harm to people. Some common examples of critical systems are transport vehicles (trains, airplanes, cars…), medical devices, and critical infrastructures (nuclear plants, oil platforms…). Safety certification intends to reduce the risk of failure to an acceptable level in compliance with standards. IEC 61508 is a reference safety standard whose use is specialized in some domains, such ISO 26262 for automotive and EN 50128 for railway. For applying these standards, the use of Model-Driven approaches based on UML Profiles is a suitable alternative. However, UML profiles are usually manually defined, which is a highly time-consuming task and error-prone. In addition, manually defined UML profiles are difficult to validate in relation to the reference standards and to the coverage of safety concepts. This paper presents the adaptation of an existing approach for automatic UML Profile generation to support the generation of UML Profiles for safety specifications that are based on IEC 61508. As a result, it is possible to reduce the time and errors that are common in a manual specification of safety UML Profiles.","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128822355","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 : 2020-11-16DOI: 10.1109/sccc51225.2020.9281200
{"title":"SCCC 2020 Cover Page","authors":"","doi":"10.1109/sccc51225.2020.9281200","DOIUrl":"https://doi.org/10.1109/sccc51225.2020.9281200","url":null,"abstract":"","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125388111","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 : 2020-11-16DOI: 10.1109/SCCC51225.2020.9281263
Héctor Cornide-Reyes, C. Valdivia, Patricio Letelier Torres, Rodolfo Villarroel
Nowadays, the massive use of agile approaches brings enormous challenges to the training of professionals with the skills required by the industry. In the educational area of software engineering, professors must have the support of technology to facilitate the process of acquisition of skills by students. The use of technology should help teachers to fulfill their role as learning facilitators and students as active agents of their learning. This article presents a web platform capable of supporting the traceability of key agile skills. This platform allows the professor to guide the process of acquiring key agile skills by defining improvement objectives, selecting agile practices and determining the expected performance levels for each activity. The platform invites students to commit to their training process and to improve in those aspects observed during the implementation of educational activities.
{"title":"AgileSkillsTrace: Plataforma web para soportar trazabilidad de habilidades ágiles clave","authors":"Héctor Cornide-Reyes, C. Valdivia, Patricio Letelier Torres, Rodolfo Villarroel","doi":"10.1109/SCCC51225.2020.9281263","DOIUrl":"https://doi.org/10.1109/SCCC51225.2020.9281263","url":null,"abstract":"Nowadays, the massive use of agile approaches brings enormous challenges to the training of professionals with the skills required by the industry. In the educational area of software engineering, professors must have the support of technology to facilitate the process of acquisition of skills by students. The use of technology should help teachers to fulfill their role as learning facilitators and students as active agents of their learning. This article presents a web platform capable of supporting the traceability of key agile skills. This platform allows the professor to guide the process of acquiring key agile skills by defining improvement objectives, selecting agile practices and determining the expected performance levels for each activity. The platform invites students to commit to their training process and to improve in those aspects observed during the implementation of educational activities.","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125930060","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 : 2020-11-16DOI: 10.1109/SCCC51225.2020.9281258
Flavio Carvalho, H. Okuno, L. Baroni, G. Guedes
The Moral Foundations Theory defines foundations to explain human moral reasoning and its role in the decision-making process, including how information is perceived and interpreted. A problem related to aspects of moral values that is currently gaining notoriety is the spread of false information known as "Fake News". Natural language processing techniques are being used in social sciences studies to deal with the Fake News detection task. This work introduces and brings details from the development of MFD-BR, a Brazilian Portuguese lexicon based on the Moral Foundations Theory, designed to measure Moral Sentiment in texts. It also contributes to Fake News detection strategies by assessing the difference in moral dimensions to distinguish between reliable sources texts and texts originated from low-reputation sources (considered by fact-checking agencies).
{"title":"A Brazilian Portuguese Moral Foundations Dictionary for Fake News classification","authors":"Flavio Carvalho, H. Okuno, L. Baroni, G. Guedes","doi":"10.1109/SCCC51225.2020.9281258","DOIUrl":"https://doi.org/10.1109/SCCC51225.2020.9281258","url":null,"abstract":"The Moral Foundations Theory defines foundations to explain human moral reasoning and its role in the decision-making process, including how information is perceived and interpreted. A problem related to aspects of moral values that is currently gaining notoriety is the spread of false information known as \"Fake News\". Natural language processing techniques are being used in social sciences studies to deal with the Fake News detection task. This work introduces and brings details from the development of MFD-BR, a Brazilian Portuguese lexicon based on the Moral Foundations Theory, designed to measure Moral Sentiment in texts. It also contributes to Fake News detection strategies by assessing the difference in moral dimensions to distinguish between reliable sources texts and texts originated from low-reputation sources (considered by fact-checking agencies).","PeriodicalId":117157,"journal":{"name":"2020 39th International Conference of the Chilean Computer Science Society (SCCC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128952338","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：