Cloud Computing Scoring System Using Sentiment Parsing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Evaluating cloud service providers is challenging due to varying service measurement indices, inaccuracies in generic sentiment analysis, and the high cost of benchmarking, which lacks an aggregate user perspective on the overall cloud computing experience.
Innovation Solution
A computer-implemented cloud computing scoring system that parses unstructured sentiment data to identify service categories, classifies sentiment using a learning seed file, and combines weighted sentiment and analytics results to produce a normalized score, enhancing the accuracy and user perspective of cloud service provider evaluations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If generic sentiment analysis is used to evaluate cloud service providers, then the evaluation process is simplified and faster, but the accuracy and domain-specific relevance of the results deteriorate
Solution Approach 1:
The patent transforms unstructured sentiment data into structured data by applying domain-specific parameter changes. It uses a parser to identify service categories and extracts specific cloud computing parameters (e.g., scalability, reliability, cost) from unstructured text, thereby improving measurement precision while maintaining evaluation efficiency through automated processing
Solution Approach 2:
The patent introduces an intermediary processing layer between raw sentiment data and final evaluation results. This layer includes a parser that structures unstructured data, a sentiment analyzer that processes structured data, and a data processor that combines results. This intermediary architecture enables both speed and accuracy by automating the transformation process
2Measurement precision
If benchmarking services are used to measure technical components of cloud platforms, then detailed performance measurements are obtained, but the cost increases substantially and the aggregate user perspective is lost
Solution Approach 1:
Instead of performing expensive actual benchmarking, the patent uses sentiment data as a copy or proxy for technical performance measurements. Users' opinions and experiences in social media posts serve as indirect measurements of technical components, providing detailed insights at a fraction of the cost of traditional benchmarking
Solution Approach 2:
The patent enables the evaluation system to self-populate with technical measurement data by automatically parsing and extracting information from user-generated sentiment data. The system serves itself by gathering performance insights from aggregate user experiences without requiring external benchmarking services
3Adaptability or versatility
If individual reports from social networking sources are gathered to compare cloud service providers, then the aggregate user perspective is obtained, but the data remains unstructured and lacks context
Solution Approach 1:
The patent segments unstructured sentiment data into distinct service categories (e.g., infrastructure, platform, software) and extracts specific cloud computing parameters from each segment. This segmentation transforms chaotic unstructured data into organized, context-rich structured data that maintains the aggregate user perspective while enabling detailed analysis
Data Source
AI summary
There is disclosed a computer-implemented cloud computing scoring system. In an embodiment, a parser receives unstructured sentiment data commenting on a scored service. The parser identifies in the unstructured sentiment data a service category of the scored service. The parser selects from the unstructured sentiment data text relating to the service category and matching one or more opinionative words and phrases listed in a keyword dictionary, thereby producing a structured comment associated with the service category. The structured comment is classified as positive or negative according to a list of exemplary sentiment data sets contained in a learning seed file. The exemplary sentiment data sets are manually assigned a positive or a negative polarity. The learning seed file is configured for enhancement by the ongoing addition of structured sentiment data, the structured sentiment data commenting on the scored service and having a polarity classification.