摘要
Many excellent studies about social networks and text analyses can be found in the literature, facilitating the rapid development of automated text analysis technology. Due to the lack of natural separators in Chinese, the text numbers and symbols also have their original literal meaning. Thus, combining Chinese characters with numbers and symbols in user-generated content is a challenge for the current analytic approaches and procedures. Therefore, we propose a new hybrid method for detecting blended numeric and symbolic homophony Chinese neologisms (BNShCNs). Interpretation of the words’ actual semantics was performed according to their independence and relative position in context. This study obtained a shortlist using a probability approach from internet-collected user-generated content; subsequently, we evaluated the shortlist by contextualizing word-embedded vectors for BNShCN detection. The experiments show that the proposed method efficiently extracted BNShCNs from user-generated content.
原文 | ???core.languages.en_GB??? |
---|---|
文章編號 | 174 |
期刊 | Information (Switzerland) |
卷 | 13 |
發行號 | 4 |
DOIs | |
出版狀態 | 已出版 - 4月 2022 |