scholarly journals A new approach for extracting and scoring aspect using SentiWordNet

2021 ◽  
Vol 22 (3) ◽  
pp. 1731
Author(s):  
Tuan Anh Tran ◽  
Jarunee Duangsuwan ◽  
Wiphada Wettayaprasit
Keyword(s):  
Business Intelligence ◽  
Vital Role ◽  
Online Information ◽  
New Approach ◽  
Customer Reviews ◽  
Aspect Extraction ◽  
The Third ◽  
Part Of Speech ◽  
Benchmark Datasets ◽  
Second Procedure

Aspect-based online information on social media plays a vital role in influencing people’s opinions when consumers concern with their decisions to make a purchase, or companies intend to pursue opinions on their product or services. Determining aspect-based opinions from the online information is necessary for business intelligence to support users in reaching their objectives. In this study, we propose the new aspect extraction and scoring system which has three procedures. The first procedure is normalizing and tagging part-of-speech for sentences of datasets. The second procedure is extracting aspects with pattern rules. The third procedure is assigning scores for aspects with SentiWordNet. In the experiments, benchmark datasets of customer reviews are used for evaluation. The performance evaluation of our proposed system shows that our proposed system has high accuracy when compared to other systems.

scholarly journals A Novel Framework for Aspect Knowledgebase Generated Automatically from Social Media Using Pattern Rules

2021 ◽  
Vol 22 (4) ◽  
Author(s):  
Tuan Anh Tran ◽  
Jarunee Duangsuwan ◽  
Wiphada Wettayaprasit
Keyword(s):  
Social Media ◽  
Performance Evaluation ◽  
Semantic Similarity ◽  
Business Intelligence ◽  
High Performance ◽  
Part Of Speech ◽  
Benchmark Datasets ◽  
Second Procedure

One of the factors improving businesses in business intelligence is summarization systems which could generate summaries based on sentiment from social media. However, these systems could not produce automatically, they used annotated datasets. To automatically produce sentiment summaries without using the annotated datasets, we propose a novel framework using pattern rules. The framework has two procedures: 1) pre-processing and 2) aspect knowledgebase generation. The first procedure is to check and correct misspelt words (bigram and unigram) by a proposed method, and tag part-of-speech all words. The second procedure is to automatically generate aspect knowledgebase used to produce sentiment summaries by the sentiment summarization systems. Pattern rules and semantic similarity-based pruning are used to automatically generate aspect knowledgebase from social media. In the experiments, eight domains from benchmark datasets of reviews are used. The performance evaluation of our proposed approach shows the high performance when compared to other approaches.

scholarly journals Automatic Aspect-Based Sentiment Summarization for Visual, Structured, and Textual Summaries

2021 ◽  
Vol 15 (1) ◽  
pp. 50-72
Author(s):  
Tuan Anh Tran ◽  
Jarunee Duangsuwan ◽  
Wiphada Wettayaprasit
Keyword(s):  
Knowledge Representation ◽  
Business Intelligence ◽  
Cell Phone ◽  
Digital Camera ◽  
Memory Capacity ◽  
Online Reviews ◽  
Sources Of Information ◽  
Language Generation ◽  
Customer Reviews ◽  
Benchmark Datasets

Online reviews are valuable sources of information to help companies to make good decisions for business intelligence. In this study, we propose an Automatic Aspect-based Sentiment Summarization (AAbSS) system that has two components and can generate a summary as an output. The first component is the Aspect-based Knowledge Representation and Selection (AKRS) used to represent reviews based on aspects and their polarities for selecting aspect-based knowledge. To represent and selection knowledge, a set of frequency of polarity opinion strength, a summation of frequency of aspect, and an information of aspect are initiated. The second component is the Summary Format Generation (SFG) used to automatically generate three kinds of formats. In this component (SFG), new representations for visual and structured summaries, and a new way of applied natural language generation for a textual summary are proposed. In the experiments, 13 domains from benchmark datasets of customer reviews, e.g. cell phone, digital camera, etc. are used. The proposed system not only fast generates summaries having good performance when compared to other summaries generated by other systems and easily updated when adding new reviews in the same domain but also does not spend memory capacity to save any raw data.

scholarly journals SEOpinion: Summarization and Exploration of Opinion from E-Commerce Websites

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 636
Author(s):  
Alhassan Mabrouk ◽  
Rebeca P. Díaz Redondo ◽  
Mohammed Kayed
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Cognitive Processing ◽  
Support Vector ◽  
Processing Capacity ◽  
Customer Reviews ◽  
Aspect Extraction ◽  
Descriptive Information ◽  
Opinion Summarization ◽  
Second Phases

Recently, it has been found that e-commerce (EC) websites provide a large amount of useful information that exceed the human cognitive processing capacity. In order to help customers in comparing alternatives when buying a product, previous research authors have designed opinion summarization systems based on customer reviews. They ignored the template information provided by manufacturers, although its descriptive information has the most useful product characteristics and texts are linguistically correct, unlike reviews. Therefore, this paper proposes a methodology coined as SEOpinion (summarization and exploration of opinions) to summarize aspects and spot opinion(s) regarding them using a combination of template information with customer reviews in two main phases. First, the hierarchical aspect extraction (HAE) phase creates a hierarchy of aspects from the template. Subsequently, the hierarchical aspect-based opinion summarization (HAOS) phase enriches this hierarchy with customers’ opinions to be shown to other potential buyers. To test the feasibility of using deep learning-based BERT techniques with our approach, we created a corpus by gathering information from the top five EC websites for laptops. The experimental results showed that recurrent neural network (RNN) achieved better results (77.4% and 82.6% in terms of F1-measure for the first and second phases, respectively) than the convolutional neural network (CNN) and the support vector machine (SVM) technique.

scholarly journals TANIAN LANJANG Pola Tata Ruang dan Kekerabatan Masyarakat Madura

2017 ◽  
Vol 10 (2) ◽  
Author(s):  
Abdul Sattar
Keyword(s):  
Family Relationship ◽  
Vital Role ◽  
The West ◽  
Architectural Pattern ◽  
The Third ◽  
House Building

This study is intended to describe the meaning of the architectural pattern and family relationship among Madurese society. There are three points that will be discussed in this article. The first, the meaning behind Madurese choice in building their home in tanian lanjang. The second, the vital role of kobhung on the pattern of tanian lanjang. The third, the metamorphosis of tanian lanjang: changable and unchangable pattern. To describe all of these aspects and to know what is really meant by Madurese society, it is extremely needed to be part of this society; living with them for a temporal time is a must. The result of this research consists of three important points. The first, the meaning of house building in tanian lanjang is to present the seniority of the inhabitants. The oldest always stays in the west position and the youngest always stay in the east position. A house also becomes a private place for women and kids. Women are also the inhabitants and the owners of houses. The second, kobhung has a vital role in tanian lanjang. It is used to become the centre of all activities done by men. The third, the existence of tongghuh and kobhung is one of unchangable pattern of tanian lanjang.

scholarly journals Overcome the Brightness and Jitter Noises in Video Inter-Frame Tampering Detection

Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 3953
Author(s):  
Han Pu ◽  
Tianqiang Huang ◽  
Bin Weng ◽  
Feng Ye ◽  
Chenbin Zhao
Keyword(s):  
Detection Method ◽  
Real Life ◽  
Vital Role ◽  
Video Forensics ◽  
Flow Algorithm ◽  
Benchmark Datasets ◽  
Media Reports ◽  
Intensity Normalization ◽  
Inter Frame ◽  
Stable Feature

Digital video forensics plays a vital role in judicial forensics, media reports, e-commerce, finance, and public security. Although many methods have been developed, there is currently no efficient solution to real-life videos with illumination noises and jitter noises. To solve this issue, we propose a detection method that adapts to brightness and jitter for video inter-frame forgery. For videos with severe brightness changes, we relax the brightness constancy constraint and adopt intensity normalization to propose a new optical flow algorithm. For videos with large jitter noises, we introduce motion entropy to detect the jitter and extract the stable feature of texture changes fraction for double-checking. Experimental results show that, compared with previous algorithms, the proposed method is more accurate and robust for videos with significant brightness variance or videos with heavy jitter on public benchmark datasets.

scholarly journals How to Solve the Problem of Evil

2019 ◽  
Vol 36 (4) ◽  
pp. 442-462 ◽  
Author(s):  
Justin Mooney ◽  
Keyword(s):  
Problem Of Evil ◽  
New Approach ◽  
Gratuitous Evil ◽  
The Third ◽  
The Problem Of Evil ◽  
Argument From Evil

One paradigmatic argument from evil against theism claims that (1) if God exists, then there is no gratuitous evil. But (2) there is gratuitous evil, so (3) God does not exist. I consider three deontological strategies for resisting this argument. Each strategy restructures existing theodicies which deny (2) so that they instead deny (1). The first two strategies are problematic on their own, but their primary weaknesses vanish when they are combined to form the third strategy, resulting in a promising new approach to the problem of evil.

scholarly journals A first step towards service-dominant logic as a new approach to overcome challenges in business intelligence

2014 ◽  
Vol 17 (2) ◽  
pp. 220-231
Author(s):  
Pamela Clavier ◽  
Hugo Lotriet ◽  
Johan Van Loggerenberg
Keyword(s):  
Literature Review ◽  
South African ◽  
Business Intelligence ◽  
New Approach ◽  
High Expectations ◽  
Dominant Logic ◽  
Interpretive Case Study ◽  
Research Findings ◽  
Banking Institution

High expectations are set for Business Intelligence (BI), yet it fails to consistently deliver accordingly: there are numerous reports of BI challenges and failures. Existing approaches to address BI challenges are largely found to be ineffective, highlighting the need for a new approach. This paper examines how BI is perceived or understood and establishes that, firstly, BI is inherently grounded in Goods-Dominant (G-D) logic and secondly, that this can be linked to the challenges that are experienced within BI. A recommendation is made for a shift to Service-Dominant (S-D) logic as a new avenue of exploration to assist in overcoming BI’s prevailing challenges. Identifying the inherent G-D logic in BI provides the first step necessary in making this shift. Research findings are based on an interpretive case study of a South African Banking institution as well as a literature review.

scholarly journals Business Intelligence in managing modern enterprises

2018 ◽  
Vol 47 (2) ◽  
pp. 64-71
Author(s):  
Mgr Kamil Soszka
Keyword(s):  
Qualitative Research ◽  
Business Intelligence ◽  
Vital Role ◽  
Comprehensive Information

In the operation of enterprises, information has always played a vital role, as it is the basis on which the decisions are made and the view regarding the upcoming events is shaped. The tool that allows for obtaining comprehensive information on the operation of a com-pany is the Business Intelligence (BI) system. Based on the results of his own qualitative research, the Author discusses the essence of BI in managing modern enterprises. He in-dicates the places where the application of this tool is most useful.

scholarly journals Rehydration of Dried-Out Specimens: a New Approach

2020 ◽  
Vol 34 (1) ◽  
pp. 73-86
Author(s):  
F. Neisskenwirth
Keyword(s):  
Water Vapor ◽  
Soft Tissue ◽  
Second Step ◽  
Phosphate Solution ◽  
Glycerol Solution ◽  
New Approach ◽  
The Third ◽  
Demineralized Water ◽  
Chemically Induced

Abstract Different procedures are proposed in the literature for the rehydration of dried-out specimens. These procedures vary greatly in their efficiency and application. This work describes a new procedure that is inspired by the literature but that avoids heating the specimens. This method was applied to reconditioning dried-out specimens from a historical collection (Swiss freshwater fishes, bird brains, and bird eyes), stored at the Naturhistorisches Museum Bern in Switzerland. The procedure consists of five steps. The first step is the softening of hardened soft tissue with benzaldehyde and demineralized water. The second step is an indirect rehydration with water vapor. The third step is a chemically induced direct hydration using a trisodium phosphate solution that allows the specimen to swell in size before being washed with water to remove all additives. Finally, the rehydrated specimen is transferred into new preserving fluid. Because the dehydrating properties of ethanol as a preservative are problematic, this paper presents the results of an experimental case study using a glycerol solution as a preservation fluid.

scholarly journals Development of a clinical algorithm for treating urethral strictures based on a large retrospective single-center cohort

F1000Research ◽  
2016 ◽  
Vol 5 ◽  
pp. 2378 ◽  
Author(s):  
Yuri Tolkach ◽  
Thomas Herrmann ◽  
Axel Merseburger ◽  
Martin Burchardt ◽  
Mathias Wolters ◽  
...  
Keyword(s):  
Clinical Decision ◽  
Low Grade ◽  
Single Center ◽  
Recurrence Rates ◽  
Decision Algorithm ◽  
Clinical Algorithm ◽  
The Third ◽  
Urethral Strictures ◽  
Male Patients ◽  
Second Procedure

Aim To analyze clinical data from male patients treated with urethrotomy and to develop a clinical decision algorithm. Materials and methods Two large cohorts of male patients with urethral strictures were included in this retrospective study, historical (1985-1995, n=491) and modern cohorts (1996-2006, n=470). All patients were treated with repeated internal urethrotomies (up to 9 sessions). Clinical outcomes were analyzed and systemized as a clinical decision algorithm. Results The overall recurrence rates after the first urethrotomy were 32.4% and 23% in the historical and modern cohorts, respectively. In many patients, the second procedure was also effective with the third procedure also feasible in selected patients. The strictures with a length ≤ 2 cm should be treated according to the initial length. In patients with strictures ≤ 1 cm, the second session could be recommended in all patients, but not with penile strictures, strictures related to transurethral operations or for patients who were 31-50 years of age. The third session could be effective in selected cases of idiopathic bulbar strictures. For strictures with a length of 1-2 cm, a second operation is possible for the solitary low-grade bulbar strictures, given that the age is > 50 years and the etiology is not post-transurethral resection of the prostate. For penile strictures that are 1-2 cm, urethrotomy could be attempted in solitary but not in high-grade strictures. Conclusions We present data on the treatment of urethral strictures with urethrotomy from a single center. Based on the analysis, a clinical decision algorithm was suggested, which could be a reliable basis for everyday clinical practice.

Sign in / Sign up

Export Citation Format

Share Document