Age Groups Classification in Social Network Using Deep Learning. Guimarães, R. G., Rosa, R. L., Gaetano, D. D., Rodríguez, D. Z., & Bressan, G. IEEE Access, 5:10805–10816, 2017. doi abstract bibtex Social networks have a large amount of data available, but often, people do not provide some of their personal data, such as age, gender, and other demographics. Although the sentiment analysis uses such data to develop useful applications in people's daily lives, there are still failures in this type of analysis, either by the restricted number of words contained in the word dictionaries or because they do not consider the most diverse parameters that can influence the sentiments in a sentence; thus, more reliable results can be obtained, if the users profile information and their writing characteristics are considered. This research suggests that one of the most relevant parameter contained in the user profile is the age group, showing that there are typical behaviors among users of the same age group, specifically, when these users write about the same topic. A detailed analysis with 7000 sentences was performed to determine which characteristics are relevant, such as, the use of punctuation, number of characters, media sharing, topics, among others; and which ones can be disregarded for the age groups classification. Different learning machine algorithms are tested for the classification of the teenager and adult age group, and the deep convolutional neural network had the best performance, reaching a precision of 0.95 in the validation tests. Furthermore, in order to validate the usefulness of the proposed model for classifying age groups, it is implemented into the enhanced sentiment metric (eSM). In the performance validation, subjective tests are performed and the eSM with the proposed model reached a root mean square error and a Pearson correlation coefficient of 0.25 and 0.94, respectively, outperforming the eSM metric, when the age group information is not available.
@article{guimaraes_age_2017,
title = {Age {Groups} {Classification} in {Social} {Network} {Using} {Deep} {Learning}},
volume = {5},
issn = {2169-3536},
doi = {10.1109/ACCESS.2017.2706674},
abstract = {Social networks have a large amount of data available, but often, people do not provide some of their personal data, such as age, gender, and other demographics. Although the sentiment analysis uses such data to develop useful applications in people's daily lives, there are still failures in this type of analysis, either by the restricted number of words contained in the word dictionaries or because they do not consider the most diverse parameters that can influence the sentiments in a sentence; thus, more reliable results can be obtained, if the users profile information and their writing characteristics are considered. This research suggests that one of the most relevant parameter contained in the user profile is the age group, showing that there are typical behaviors among users of the same age group, specifically, when these users write about the same topic. A detailed analysis with 7000 sentences was performed to determine which characteristics are relevant, such as, the use of punctuation, number of characters, media sharing, topics, among others; and which ones can be disregarded for the age groups classification. Different learning machine algorithms are tested for the classification of the teenager and adult age group, and the deep convolutional neural network had the best performance, reaching a precision of 0.95 in the validation tests. Furthermore, in order to validate the usefulness of the proposed model for classifying age groups, it is implemented into the enhanced sentiment metric (eSM). In the performance validation, subjective tests are performed and the eSM with the proposed model reached a root mean square error and a Pearson correlation coefficient of 0.25 and 0.94, respectively, outperforming the eSM metric, when the age group information is not available.},
journal = {IEEE Access},
author = {Guimarães, R. G. and Rosa, R. L. and Gaetano, D. De and Rodríguez, D. Z. and Bressan, G.},
year = {2017},
keywords = {文本分类, 文本挖掘},
pages = {10805--10816},
}
Downloads: 0
{"_id":"Kykohm9s9BpqDmaZ3","bibbaseid":"guimares-rosa-gaetano-rodrguez-bressan-agegroupsclassificationinsocialnetworkusingdeeplearning-2017","author_short":["Guimarães, R. G.","Rosa, R. L.","Gaetano, D. D.","Rodríguez, D. Z.","Bressan, G."],"bibdata":{"bibtype":"article","type":"article","title":"Age Groups Classification in Social Network Using Deep Learning","volume":"5","issn":"2169-3536","doi":"10.1109/ACCESS.2017.2706674","abstract":"Social networks have a large amount of data available, but often, people do not provide some of their personal data, such as age, gender, and other demographics. Although the sentiment analysis uses such data to develop useful applications in people's daily lives, there are still failures in this type of analysis, either by the restricted number of words contained in the word dictionaries or because they do not consider the most diverse parameters that can influence the sentiments in a sentence; thus, more reliable results can be obtained, if the users profile information and their writing characteristics are considered. This research suggests that one of the most relevant parameter contained in the user profile is the age group, showing that there are typical behaviors among users of the same age group, specifically, when these users write about the same topic. A detailed analysis with 7000 sentences was performed to determine which characteristics are relevant, such as, the use of punctuation, number of characters, media sharing, topics, among others; and which ones can be disregarded for the age groups classification. Different learning machine algorithms are tested for the classification of the teenager and adult age group, and the deep convolutional neural network had the best performance, reaching a precision of 0.95 in the validation tests. Furthermore, in order to validate the usefulness of the proposed model for classifying age groups, it is implemented into the enhanced sentiment metric (eSM). In the performance validation, subjective tests are performed and the eSM with the proposed model reached a root mean square error and a Pearson correlation coefficient of 0.25 and 0.94, respectively, outperforming the eSM metric, when the age group information is not available.","journal":"IEEE Access","author":[{"propositions":[],"lastnames":["Guimarães"],"firstnames":["R.","G."],"suffixes":[]},{"propositions":[],"lastnames":["Rosa"],"firstnames":["R.","L."],"suffixes":[]},{"propositions":[],"lastnames":["Gaetano"],"firstnames":["D.","De"],"suffixes":[]},{"propositions":[],"lastnames":["Rodríguez"],"firstnames":["D.","Z."],"suffixes":[]},{"propositions":[],"lastnames":["Bressan"],"firstnames":["G."],"suffixes":[]}],"year":"2017","keywords":"文本分类, 文本挖掘","pages":"10805–10816","bibtex":"@article{guimaraes_age_2017,\n\ttitle = {Age {Groups} {Classification} in {Social} {Network} {Using} {Deep} {Learning}},\n\tvolume = {5},\n\tissn = {2169-3536},\n\tdoi = {10.1109/ACCESS.2017.2706674},\n\tabstract = {Social networks have a large amount of data available, but often, people do not provide some of their personal data, such as age, gender, and other demographics. Although the sentiment analysis uses such data to develop useful applications in people's daily lives, there are still failures in this type of analysis, either by the restricted number of words contained in the word dictionaries or because they do not consider the most diverse parameters that can influence the sentiments in a sentence; thus, more reliable results can be obtained, if the users profile information and their writing characteristics are considered. This research suggests that one of the most relevant parameter contained in the user profile is the age group, showing that there are typical behaviors among users of the same age group, specifically, when these users write about the same topic. A detailed analysis with 7000 sentences was performed to determine which characteristics are relevant, such as, the use of punctuation, number of characters, media sharing, topics, among others; and which ones can be disregarded for the age groups classification. Different learning machine algorithms are tested for the classification of the teenager and adult age group, and the deep convolutional neural network had the best performance, reaching a precision of 0.95 in the validation tests. Furthermore, in order to validate the usefulness of the proposed model for classifying age groups, it is implemented into the enhanced sentiment metric (eSM). In the performance validation, subjective tests are performed and the eSM with the proposed model reached a root mean square error and a Pearson correlation coefficient of 0.25 and 0.94, respectively, outperforming the eSM metric, when the age group information is not available.},\n\tjournal = {IEEE Access},\n\tauthor = {Guimarães, R. G. and Rosa, R. L. and Gaetano, D. De and Rodríguez, D. Z. and Bressan, G.},\n\tyear = {2017},\n\tkeywords = {文本分类, 文本挖掘},\n\tpages = {10805--10816},\n}\n\n","author_short":["Guimarães, R. G.","Rosa, R. L.","Gaetano, D. D.","Rodríguez, D. Z.","Bressan, G."],"key":"guimaraes_age_2017","id":"guimaraes_age_2017","bibbaseid":"guimares-rosa-gaetano-rodrguez-bressan-agegroupsclassificationinsocialnetworkusingdeeplearning-2017","role":"author","urls":{},"keyword":["文本分类","文本挖掘"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/wybert","dataSources":["TJkbwzD8s2wCxBy6Y"],"keywords":["文本分类","文本挖掘"],"search_terms":["age","groups","classification","social","network","using","deep","learning","guimarães","rosa","gaetano","rodríguez","bressan"],"title":"Age Groups Classification in Social Network Using Deep Learning","year":2017}