公开(公告)号：US07877345B2

公开(公告)日：2011-01-25

申请号：US12395239

申请日：2009-02-27

Applicant: Kamal P. Nigam ,  Matthew F. Hurst

Inventor： Kamal P. Nigam ,  Matthew F. Hurst

IPC: G06F17/00 ,  G06N7/00 ,  G06N7/08

CPC classification number: G06F17/274 ,  G06Q30/02

Abstract: The present application presents methods for performing topical sentiment analysis on electronically stored communications employing fusion of polarity and topicality. The present application also provides methods for utilizing shallow NLP techniques to determine the polarity of an expression. The present application also provides a method for tuning a domain-specific polarity lexicon for use in the polarity determination. The present application also provides methods for computing a numeric metric of the aggregate opinion about some topic expressed in a set of expressions.

Abstract translation: 本申请提出了使用极性和话题的融合来进行电子存储通信的局部情绪分析的方法。 本申请还提供了利用浅层NLP技术来确定表达式的极性的方法。 本申请还提供了一种用于调整用于极性确定的域特定极性词典的方法。 本申请还提供了用于计算关于在一组表达式中表达的某个主题的聚合意见的数值度量的方法。

公开(公告)号：US20100042910A1

公开(公告)日：2010-02-18

申请号：US12193148

申请日：2008-08-18

Applicant: Dragos Manolescu ,  Matthew F. Hurst

Inventor： Dragos Manolescu ,  Matthew F. Hurst

IPC: G06F17/00

CPC classification number: G06F17/241 ,  G06F17/30867 ,  G06Q10/10

Abstract: Techniques and systems for assisting an author in creating content for social media (e.g., blog posts, microblogs, tweets, etc.) are disclosed, wherein hints are provided to the author as a function of social media stored in a social media knowledge store. Social media is collected and stored in a social media knowledge store according to some criteria. Upon the happening of some predetermined event, for example, relevant information is retrieved from the social media knowledge store. The relevancy of information may be a function of editing context (provided by the author) and/or social media behavior, for example. The relevant information may be translated into hints that provide an author with suggestions and/or corrections, for example. This information is provided to the author through a social media environment (e.g., an authoring tool) that may be also be capable of receiving input from the author and outputting editing context.

Abstract translation: 公开了用于协助作者为社交媒体创建内容（例如博客文章，微博，推文等）的技术和系统，其中作为存储在社交媒体知识存储中的社交媒体的功能，向作者提供提示。 根据一些标准，社交媒体被收集并存储在社交媒体知识库中。 在发生某些预定事件时，例如，从社交媒体知识存储器检索相关信息。 例如，信息的相关性可以是编辑上下文（由作者提供）和/或社交媒体行为的功能。 相关信息可能被翻译成提示作者提供建议和/或更正的提示。 该信息通过可能还能够从作者接收输入并输出编辑上下文的社交媒体环境（例如，创作工具）提供给作者。

公开(公告)号：US20090319449A1

公开(公告)日：2009-12-24

申请号：US12143765

申请日：2008-06-21

Applicant: Michael Gamon ,  Sumit Basu ,  Dmitriy A. Belenko ,  Danyel A. Fisher ,  Arnd C. Konig ,  Matthew F. Hurst

Inventor： Michael Gamon ,  Sumit Basu ,  Dmitriy A. Belenko ,  Danyel A. Fisher ,  Arnd C. Konig ,  Matthew F. Hurst

IPC: G06F15/18 ,  G06F17/30 ,  G06N5/02

CPC classification number: G06F17/30014

Abstract: An overwhelming number of articles are available everyday via the internet. Unfortunately, it is impossible to peruse more than a handful, and it is difficult to ascertain an article's social context. The techniques disclosed herein address this problem by harnessing implicit and explicit contextual information from social media. By extracting text surrounding a hyperlink to an article in a post and assessing the article as a function of content surrounding the hyperlink, an article's social context is determined and presented. Additionally, articles that are sufficiently similar in content may be grouped to establish a many-to-one relationship between posts and an article, creating a more accurate assessment.

Abstract translation: 每天通过互联网可以获得绝大多数的文章。 不幸的是，不可能仔细阅读，而且很难确定文章的社会背景。 本文所揭示的技术通过利用来自社交媒体的隐含和明确的上下文信息来解决这个问题。 通过提取文章中超文本文章中的文章，并根据超链接的内容评估文章，确定并呈现文章的社会语境。 此外，内容足够相似的文章可以被分组以在帖子和文章之间建立多对一关系，从而创建更准确的评估。

公开(公告)号：US20090164417A1

公开(公告)日：2009-06-25

申请号：US12395239

申请日：2009-02-27

Applicant: Kamal P. Nigam ,  Matthew F. Hurst

Inventor： Kamal P. Nigam ,  Matthew F. Hurst

IPC: G06F17/30

CPC classification number: G06F17/274 ,  G06Q30/02

Abstract: The present application presents methods for performing topical sentiment analysis on electronically stored communications employing fusion of polarity and topicality. The present application also provides methods for utilizing shallow NLP techniques to determine the polarity of an expression. The present application also provides a method for tuning a domain-specific polarity lexicon for use in the polarity determination. The present application also provides methods for computing a numeric metric of the aggregate opinion about some topic expressed in a set of expressions.

Abstract translation: 本申请提出了使用极性和话题的融合来进行电子存储通信的局部情绪分析的方法。 本申请还提供了利用浅层NLP技术来确定表达式的极性的方法。 本申请还提供了一种用于调整用于极性确定的域特定极性词典的方法。 本申请还提供了用于计算关于在一组表达式中表达的某个主题的聚合意见的数值度量的方法。