Automated Opinion Mining System for Unstructured Text Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Companies face challenges in efficiently collecting and analyzing end-user opinions on products, services, and features due to low response rates from traditional surveys and the time-consuming nature of mining opinions from various online sources, such as review websites and forums.

Innovation Solution

A system and method for evaluating reviews with unstructured text, involving segment splitting, lexical category assignment, feature and opinion word identification, sentiment scoring, and opinion summarization to provide actionable insights, including a scraper network to gather and normalize opinions from diverse online platforms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional paper surveys and telephone inquiries are used to collect end-user opinions, then companies can obtain direct user feedback, but response rates are extremely low and the process is inefficient

Engineering Contradiction:

Improveaccuracy of opinion collectionVSAvoidefficiency of opinion collection

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces manual mechanical processes (paper surveys, telephone calls) with an automated electronic system that uses web crawlers, natural language processing, and database technologies to automatically collect, process, and analyze end-user opinions from multiple online sources, thereby maintaining measurement precision while dramatically improving productivity

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by allowing end-users to automatically publish their opinions on third-party websites without being directly contacted by the company, while the automated system simultaneously collects and analyzes these opinions, eliminating the need for manual survey distribution and follow-up

Inventive Principle:

Principle #25Self-service

2Ease of operation

If electronic surveys are distributed online to collect end-user opinions, then convenience is improved and more users are willing to respond, but the majority of users still do not complete the surveys

Engineering Contradiction:

Improveconvenience of opinion submissionVSAvoidcompletion rate of opinion collection

Core Design Contradiction:

Ease of operationVSProductivity

Solution Approach 1:

Instead of actively requesting opinions from users through surveys, the system inverts the approach by passively collecting opinions that users have already voluntarily published on third-party websites, thereby achieving high completion rates by leveraging user-initiated feedback rather than company-initiated requests

Inventive Principle:

Principle #13The other way round (Inversion)

3Loss of information

If companies manually mine end-user opinions from various online sources including review websites and forums, then comprehensive opinion data can be gathered, but the process is extremely time-consuming

Engineering Contradiction:

Improvecompleteness of opinion dataVSAvoidtime required for opinion mining

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The patent segments the opinion mining process into distinct automated components: web crawlers that scrape data from multiple sources, natural language processing modules that analyze text, and database systems that store and retrieve information, allowing comprehensive data collection while eliminating manual time investment through parallel automated processing

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system introduces automated intermediary tools including web crawlers, natural language processing algorithms, and database management systems that mediate between diverse online opinion sources and company analysts, enabling comprehensive data gathering from multiple platforms without requiring manual intervention for each source

Inventive Principle:

Principle #24Intermediary (Mediator)

4Adaptability or versatility

If companies analyze opinions from multiple competitor products and services, then market positioning insights can be obtained, but the complexity of processing and comparing data increases significantly

Engineering Contradiction:

Improveability to compare across products and competitorsVSAvoidcomplexity of opinion analysis system

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent applies parameter changes by transforming unstructured opinion text into standardized structured data with consistent formatting, categorization, and scoring parameters, enabling efficient comparison across different products, services, and competitors while reducing the complexity of analyzing diverse data sources through uniform parameter sets

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS8645395B2System and methods for evaluating feature opinions for products, services, and entities

Publication Date: 2014.02.04 INCONTACT INC

AI summary

A system for evaluating a review having unstructured text comprises a segment splitter for separating at least a portion of the unstructured text into one or more segments, each segment comprising one or more words; a segment parser coupled to the segment splitter for assigning one or more lexical categories to one or more of the one or more words of each segment; an information extractor coupled to the segment parser for identifying a feature word and an opinion word contained in the one or more segments; and a sentiment rating engine coupled to the information extractor for calculating an opinion score based upon an opinion grouping, the opinion grouping including at least the feature word and the opinion word identified by the information extractor.