Analyzing Social Network Data Using Deep Neural Networks: A Case Study Using Twitter Posts
碩士 === 國立政治大學 === 資訊科學系 === 107 === Interaction on various social networking platforms has become an important part of our daily life. Apart from text messages, image is also a popular media format utilized for online communication. Text or image alone, however, cannot fully convey the ideas that us...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2018
|
Online Access: | http://ndltd.ncl.edu.tw/handle/wtqyh3 |
id |
ndltd-TW-107NCCU5394005 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-107NCCU53940052019-05-16T01:40:45Z http://ndltd.ncl.edu.tw/handle/wtqyh3 Analyzing Social Network Data Using Deep Neural Networks: A Case Study Using Twitter Posts 應用深度學習架構於社群網路資料分析:以Twitter圖文資料為例 Yang, Tzu-Hsuan 楊子萲 碩士 國立政治大學 資訊科學系 107 Interaction on various social networking platforms has become an important part of our daily life. Apart from text messages, image is also a popular media format utilized for online communication. Text or image alone, however, cannot fully convey the ideas that users wish to express. In the thesis, we employ computer vision and word embedding techniques to analyze the relationship between image content and text messages and explore the rich information entangled. The limitation on the total number of characters compels Twitter users to compose their messages more succinctly, suggesting a stronger association between text and image. In this study, we collected all tweets which include keywords related to Taiwan during 2017. After data cleaning, we apply machine learning techniques to classify tweets into to ‘travel’ and ‘non-travel’ types. This is achieved by employing deep neural networks to process and integrate text and image information. Within each class, we use hierarchical clustering to further partition the data into different clusters and investigate their characteristics. Through this research, we expect to identify the relationship between text and images in a tweet and gain more understanding of the properties of tweets on social networking platforms. The proposed framework and corresponding analytical results should also prove useful for qualitative research. Liao, Wen-Hung 廖文宏 2018 學位論文 ; thesis 73 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立政治大學 === 資訊科學系 === 107 === Interaction on various social networking platforms has become an important part of our daily life. Apart from text messages, image is also a popular media format utilized for online communication. Text or image alone, however, cannot fully convey the ideas that users wish to express. In the thesis, we employ computer vision and word embedding techniques to analyze the relationship between image content and text messages and explore the rich information entangled.
The limitation on the total number of characters compels Twitter users to compose their messages more succinctly, suggesting a stronger association between text and image. In this study, we collected all tweets which include keywords related to Taiwan during 2017. After data cleaning, we apply machine learning techniques to classify tweets into to ‘travel’ and ‘non-travel’ types. This is achieved by employing deep neural networks to process and integrate text and image information. Within each class, we use hierarchical clustering to further partition the data into different clusters and investigate their characteristics.
Through this research, we expect to identify the relationship between text and images in a tweet and gain more understanding of the properties of tweets on social networking platforms. The proposed framework and corresponding analytical results should also prove useful for qualitative research.
|
author2 |
Liao, Wen-Hung |
author_facet |
Liao, Wen-Hung Yang, Tzu-Hsuan 楊子萲 |
author |
Yang, Tzu-Hsuan 楊子萲 |
spellingShingle |
Yang, Tzu-Hsuan 楊子萲 Analyzing Social Network Data Using Deep Neural Networks: A Case Study Using Twitter Posts |
author_sort |
Yang, Tzu-Hsuan |
title |
Analyzing Social Network Data Using Deep Neural Networks: A Case Study Using Twitter Posts |
title_short |
Analyzing Social Network Data Using Deep Neural Networks: A Case Study Using Twitter Posts |
title_full |
Analyzing Social Network Data Using Deep Neural Networks: A Case Study Using Twitter Posts |
title_fullStr |
Analyzing Social Network Data Using Deep Neural Networks: A Case Study Using Twitter Posts |
title_full_unstemmed |
Analyzing Social Network Data Using Deep Neural Networks: A Case Study Using Twitter Posts |
title_sort |
analyzing social network data using deep neural networks: a case study using twitter posts |
publishDate |
2018 |
url |
http://ndltd.ncl.edu.tw/handle/wtqyh3 |
work_keys_str_mv |
AT yangtzuhsuan analyzingsocialnetworkdatausingdeepneuralnetworksacasestudyusingtwitterposts AT yángzixuān analyzingsocialnetworkdatausingdeepneuralnetworksacasestudyusingtwitterposts AT yangtzuhsuan yīngyòngshēndùxuéxíjiàgòuyúshèqúnwǎnglùzīliàofēnxīyǐtwittertúwénzīliàowèilì AT yángzixuān yīngyòngshēndùxuéxíjiàgòuyúshèqúnwǎnglùzīliàofēnxīyǐtwittertúwénzīliàowèilì |
_version_ |
1719178052923031552 |