首页> 外文期刊>New scientist >Al learns to spot sarcasm in your tweets
【24h】

Al learns to spot sarcasm in your tweets

机译:Al学习在推文中发现讽刺

获取原文
获取原文并翻译 | 示例
           

摘要

Picking up on sarcasm online can be hard even for humans. For computers, its often a major headache. But now a machine learning system has learned to spot when you're being sarcastic just by reading your past tweets. Mining comments on social media is big business. Advertisers track our attitudes and moods, companies and governments follow public opinion. But people being sarcastic and saying the opposite of what they mean makes this tricky. So Silvio Amir at the University of Lisbon, Portugal, and his colleagues turned to machine learning. They trained the system to spot sarcasm on Twitter simply by looking at a user's tweets. The software builds up a rich enough picture of a person that it can deduce when they're being sarcastic, correctly interpreting tweets such as "ok thanks for being a great caring personl" and "@BernieSanders and obama doing a great job."
机译:即使对人类来说,在网上嘲讽也很困难。对于计算机而言,这通常是头疼的问题。但是现在,机器学习系统已经学会了仅通过阅读您过去的推文就能发现您何时处于讽刺状态。在社交媒体上挖掘评论是一件大事。广告商追踪我们的态度和情绪,公司和政府遵循公众舆论。但是人们很讽刺,说出了他们的意思相反,这很棘手。因此,葡萄牙里斯本大学的Silvio Amir和他的同事们转向了机器学习。他们培训了该系统,只需查看用户的推文即可在Twitter上发现讽刺。该软件可以建立一个足够丰富的人物形象,当他们被讽刺时,可以推断出该人物,正确地解释了诸如“好,谢谢你成为一个有爱心的人”和“ @BernieSanders和奥巴马所做的出色工作”之类的推文。

著录项

  • 来源
    《New scientist》 |2016年第3086期|22-22|共1页
  • 作者

    Edd Gent;

  • 作者单位
  • 收录信息 美国《科学引文索引》(SCI);美国《化学文摘》(CA);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号