Mining product aspects from opinion text
a technology of opinion text and product aspects, applied in the field of automatic textual analysis, can solve the problems of not being easily accessible to users, latent and therefore not readily available, and reading more than a handful of reviews is impractical for buyers, and it is impractical for a single forum user to review each pos
Inactive Publication Date: 2016-08-11
INT BUSINESS MASCH CORP
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Benefits of technology
The present patent provides a method for extracting aspects from a text stream using subject-verb-object triples. The process involves parsing a text stream and selecting verbs that match a predefined list. The subject of each selected sentence is identified as an aspect candidate. The aspect candidate is then generated as a n-gram and the frequency at which it is generated is determined. A number of these n-grams are selected as aspects based on the frequency with which they are generated. The technical effect of this method is to provide a way for extracting relevant aspects from a text stream without requiring human interpretation.
Problems solved by technology
This information may be latent and therefore not readily accessible to a user.
The product may be associated with thousands of reviews, and reading more than a handful of the reviews may be impractical for the buyer.
It may be impractical for a single forum user to review each post.
The result may be that potentially valuable the information in such reviews or posts goes unused.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0010]Generally, embodiments of the present disclosure provide for extraction of Aspects from text. According to one embodiment, an Aspect may correspond to an n-gram generated using a subject of the text.
[0011]FIG. 1 is a block diagram of an Aspect Extraction System 100 for extracting one or more Aspects from text, according to an embodiment of the present disclosure. The Aspect Extraction System 100 may be a computing device having a tangible Storage Device 130 and a Program 102 for execution by a processor (not shown). The Program 102 may include a Data Storage Module 110 that loads and stores one or more of the following data types from / to the Storage Device 130 (or from / to another tangible storage device): Text Collection(s) 112, Lexicon(s) 114, and Database(s) 116. The Program 102 may also include an Opinion Analysis Module 120 which may communicate with the Data Storage Module 110 to obtain data to analyze, and to provide analysis results that may be stored on the tangible St...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
A text stream having one or more sentences is received, and any number of the one or more sentences are parsed to determine corresponding subject-verb-object (SVO) triples. Each sentence whose corresponding SVO triple contains an identified verb is selected, based on the identified verb, or a lemma of the identified verb, matching a predefined verb. A subject of each selected sentence is identified as an aspect candidate. Each identified aspect candidate is tokenized and normalized. One or more n-grams are generated for each tokenized and normalized aspect candidate. For each generated n-gram, a frequency at which the n-gram is generated is determined. A number of the generated n-grams are selected as aspects based on the frequency with which the number of n-grams are generated.
Description
FIELD OF THE INVENTION[0001]The present disclosure generally relates to automated textual analysis, and more particularly to determining textually expressed sentiments.BACKGROUND[0002]Unstructured digital data such as unstructured digital text data often contains useful information. This information may be latent and therefore not readily accessible to a user. For example, opinions expressed in online reviews for a product may help a potential buyer decide whether to purchase that product. The product may be associated with thousands of reviews, and reading more than a handful of the reviews may be impractical for the buyer. In another example, a discussion thread in an online forum may contain hundreds or thousands of posts. It may be impractical for a single forum user to review each post. The result may be that potentially valuable the information in such reviews or posts goes unused.BRIEF SUMMARY[0003]Embodiments of the present disclosure provide a method, system, and computer p...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(United States)
IPC IPC(8): G06F17/30G06F17/27
CPCG06F17/30719G06F17/30699G06F17/277G06F17/271G06F16/335G06F16/345G06F40/211G06F40/284
Inventor GOU, LIANGHU, MENGDIELI, YUNYAOYANG, HUAHAI
Owner INT BUSINESS MASCH CORP