公开(公告)号：US20160371350A1

公开(公告)日：2016-12-22

申请号：US15114198

申请日：2014-04-30

Applicant: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

Inventor： Ming C. Hao ,  Michael Hund ,  Christian Rohrdantz ,  Riddhiman Ghosh ,  Nelson L. Chang ,  Meichun Hsu ,  Daniel Keim

IPC: G06F17/30 ,  G06T11/60

CPC classification number: G06F16/26 ,  G06F16/2272 ,  G06F16/24578 ,  G06F16/35 ,  G06T11/60

Abstract: Selected topics are identified from records based on scoring candidate terms in the records according to a user-specified metric and at least one further metric selected from among frequencies of occurrence of records pertaining to the respective candidate terms, and negativity of sentiment expressed with respect to the candidate terms in the records. A visualization is generated that includes bubbles representing the respective topics, the bubbles including pixels representing corresponding records, where a given one of the bubbles has a shape dependent upon a number of records represented by the given bubble and a time interval represented by the given bubble. Visual indicators are assigned to the pixels in the given bubble according to values of an attribute expressed in the corresponding records for the topic represented by the given bubble.

Abstract translation: 所选择的主题是根据记录中根据用户指定的度量记录中的评分候选项的记录和从相应候选项的有关记录的出现频率中选出的至少一个另外的度量来识别的，以及相对于 记录中的候选词。 生成可视化，其包括表示相应主题的气泡，气泡包括表示对应记录的像素，其中给定的一个气泡具有取决于由给定气泡表示的记录数量的形状和由给定气泡表示的时间间隔 。 根据给定气泡表示的主题的相应记录中表示的属性的值，将可视指示符分配给给定气泡中的像素。

公开(公告)号：US20160307114A1

公开(公告)日：2016-10-20

申请号：US15044351

申请日：2016-02-16

Applicant: Hewlett Packard Enterprise Development LP

Inventor： Riddhiman Ghosh ,  Mohamed E. Dekhil ,  Lei Zhang

IPC: G06N99/00 ,  G06F17/27 ,  G06F17/30

CPC classification number: G06N20/00 ,  G06F16/355 ,  G06F17/2785 ,  G06Q30/02

Abstract: There is provided a computer-implemented method of performing sentiment analysis. An exemplary method comprises performing a first sentiment analysis on microblogging data based on a method using an opinion lexicon. The method also includes training a classifier using training data from the first sentiment analysis. Additionally, the method includes identifying a new opinion term in the microblogging data by performing a statistical test. The new opinion terms are not in the opinion lexicon. The method also includes identifying new microblogging data based on the new opinion term. Further, the method includes performing a second sentiment analysis on the new microblogging data using the classifier.