.png){kind=icon}
.png){kind=icon}
Return
Emotion aware feature based opining mining on large scale data by exploring hypergraph with helly property
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-021-11311-2.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Customers making product purchases and businesses looking for feedback on their items have grown to rely on feature-based online comments provided by users on e-commerce platforms. As a result, it's critical to create aspect-based opinion mining frameworks that focus on obtaining consumers' feature-based judgments about products. Nowadays people convey their opinions and provide their experiences that significantly affect new purchasers in buying products, thus it leads to maintenance of large data sets. This massive amount of data is extremely beneficial for studying user preferences, desires, and behavior in relation to a product. E-commerce service providers face the difficult task of evaluating such vast amounts of data in order to derive client feedback. In order to resolve this issue, we explored Hypergraph with Helly property to perform emotion aware aspect-based opinion mining on real-world customer review data. In this paper, we are proposing a new distributed Hypergraph with Helly property algorithm for opinion mining to work on distributed Hadoop environment. Because of the large size data set, the suggested feature-based opinion mining system surpasses the alternative approaches in terms of greater accuracy and less time complexity, according to the performance evaluation using state-of-the-art methods. The proposed methodology is more efficient for extracting aspect-sentiment, categorizing, and summarizing online product reviews, according to the experimental results.
Keywords:
Feature based opining mining
Hypergraph
Helly property
Feature selection
Large scale data set
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3
Papers:
1.9W
Citations:
3.2W