scholarly journals CIAA-RepDroid: A Fine-Grained and Probabilistic Reputation Scheme for Android Apps Based on Sentiment Analysis of Reviews

2020 ◽  
Vol 12 (9) ◽  
pp. 145
Author(s):  
Franklin Tchakounté ◽  
Athanase Esdras Yera Pagor ◽  
Jean Claude Kamgang ◽  
Marcellin Atemkeng
Keyword(s):  
Sentiment Analysis ◽  
Quantitative Comparison ◽  
Rating Systems ◽  
Security Vulnerabilities ◽  
Source Codes ◽  
Fine Grained ◽  
Android Apps ◽  
Google Play ◽  
Application Execution

To keep its business reliable, Google is concerned to ensure the quality of apps on the store. One crucial aspect concerning quality is security. Security is achieved through Google Play protect and anti-malware solutions. However, they are not totally efficient since they rely on application features and application execution threads. Google provides additional elements to enable consumers to collectively evaluate applications providing their experiences via reviews or showing their satisfaction through rating. The latter is more informal and hides details of rating whereas the former is textually expressive but requires further processing to understand opinions behind it. Literature lacks approaches which mine reviews through sentiment analysis to extract useful information to improve the security aspects of provided applications. This work goes in this direction and in a fine-grained way, investigates in terms of confidentiality, integrity, availability, and authentication (CIAA). While assuming that reviews are reliable and not fake, the proposed approach determines review polarities based on CIAA-related keywords. We rely on the popular classifier Naive Bayes to classify reviews into positive, negative, and neutral sentiment. We then provide an aggregation model to fusion different polarities to obtain application global and CIAA reputations. Quantitative experiments have been conducted on 13 applications including e-banking, live messaging and anti-malware apps with a total of 1050 security-related reviews and 7,835,322 functionality-related reviews. Results show that 23% of applications (03 apps) have a reputation greater than 0.5 with an accent on integrity, authentication, and availability, while the remaining 77% has a polarity under 0.5. Developers should make a lot of effort in security while developing codes and that more efforts should be made to improve confidentiality reputation. Results also show that applications with good functionality-related reputation generally offer a bad security-related reputation. This situation means that even if the number of security reviews is low, it does not mean that the security aspect is not a consumer preoccupation. Unlike, developers put much more time to test whether applications work without errors even if they include possible security vulnerabilities. A quantitative comparison against well-known rating systems reveals the effectiveness and robustness of CIAA-RepDroid to repute apps in terms of security. CIAA-RepDroid can be associated with existing rating solutions to recommend developers exact CIAA aspects to improve within source codes.

scholarly journals CIAA-RepDroid: A Fine-Grained and Probabilistic Reputation Scheme of Android Apps Based on Sentiment Analysis of Reviews

2020 ◽  
Author(s):  
Franklin Tchakounté ◽  
Athanase Esdras Yera Pagore ◽  
Jean Claude Kamgang ◽  
Marcellin Atemkeng
Keyword(s):  
Sentiment Analysis ◽  
Quantitative Comparison ◽  
Rating Systems ◽  
Security Vulnerabilities ◽  
Source Codes ◽  
Fine Grained ◽  
Android Apps ◽  
Google Play ◽  
Application Execution

To keep its business reliable, Google is concerned to ensure quality of apps on the store. One crucial aspect concerning quality is security. Security is achieved through Google Play protect and anti-malware solutions. However, they are not totally efficient since they rely on application features and application execution threads. Google provides additional elements to enable consumers to collectively evaluate applications providing their experiences via reviews or showing their satisfaction through rating. The latter is more informal and hides details of rating whereas the former is textually expressive but requires further processing to understand opinions behind. Literature lacks approaches which mine reviews through sentiment analysis to extract useful information to improve security aspects of provided applications. This work goes in this direction and in a fine-grained way, investigates in terms of confidentiality, integrity, availability and authentication (CIAA). While assuming that reviews are reliable and not fake, the proposed approach determines review polarities based on CIAA-related keywords. We rely on the popular classifier Naive Bayes to classify reviews into positive, negative and neutral sentiment. We then provide an aggregation model to fusion different polarities to obtain application global and CIAA reputations. Quantitative experiments have been conducted on 13 applications including e-banking, live messaging and anti-malware apps with a total of 1050 security-related reviews and 7.835.322 functionality-related reviews. Results show that 23% of applications (03 apps) have a reputation greater than 0.5 with an accent on integrity, authentication and availability, while the remaining 77% has a polarity under 0.5. Developers should make lot of efforts in security while developing codes and that more efforts should be made to improve confidentiality reputation. Results also show that applications with good functionality-related reputation generally offer bad security-related reputation. This situation means that even if the number of security reviews is low, it does not mean that security aspect is not a consumer preoccupation. Unlike, developers put much more time to test whether applications works without errors even if they include possible security vulnerabilities. A quantitative comparison against well-known rating systems reveals effectiveness and robustness of CIAA-RepDroid to repute apps in terms of security. CIAA-RepDroid can be associated to existing rating solutions to recommend developers exact CIAA aspects to improve within source codes.

scholarly journals A Security-Related Reputation Scheme of Android Apps Based on NLP Analysis of Comments

2020 ◽  
Author(s):  
Franklin Tchakounté ◽  
Athanase Esdras Yera Pagore ◽  
Marcellin Atemkeng ◽  
Jean Claude Kamgang
Keyword(s):  
Natural Language Processing ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Text Analysis ◽  
Positive Functional ◽  
Fine Grained ◽  
Android Apps ◽  
Depth Analysis ◽  
Android Applications ◽  
Google Play

Comments are exploited by product vendors to measure satisfaction of consumers. With the advent of Natural Language Processing (NLP), comments on Google Play can be processed to extract knowledge on applications such as their reputation. Proposals in that direction are either informal or interested merely on functionality. Unlike, this work aims to determine reputation of Android applications in terms of confidentiality, integrity, availability and authentication (CIAA). This work proposes a model of assessing app reputation relying on sentiment analysis and text analysis of comments. While assuming that comments are reliable, we collect Google Play applications subject to comments which include security keywords. An in-depth analysis of keywords based on Naive Bayes classification is made to provide polarity of any comment. Based on comment polarity, reputation is evaluated for the whole application. Experiments made on real applications including dozens to billions of comments, reveal that developers lack to make efforts to guarantee CIAA services. A fine-grained analysis shows that not security reputed applications can be reputed in specific CIAA services. Results also show that applications with negative security polarities display in general positive functional polarities. This result suggests that security checking should include careful comment analysis to improve security of applications.

scholarly journals Triple Classification Using Regions and Fine-Grained Entity Typing

2019 ◽  
Vol 33 ◽  
pp. 77-85 ◽  
Author(s):  
Tiansi Dong ◽  
Zhigang Wang ◽  
Juanzi Li ◽  
Christian Bauckhage ◽  
Armin B. Cremers
Keyword(s):  
Zero Energy ◽  
Tree Structures ◽  
Source Codes ◽  
Geometric Process ◽  
Fine Grained ◽  
Literature Source ◽  
Benchmark Datasets ◽  
Triple H

A Triple in knowledge-graph takes a form that consists of head, relation, tail. Triple Classification is used to determine the truth value of an unknown Triple. This is a hard task for 1-to-N relations using the vector-based embedding approach. We propose a new region-based embedding approach using fine-grained type chains. A novel geometric process is presented to extend the vectors of pre-trained entities into n-balls (n-dimensional balls) under the condition that head balls shall contain their tail balls. Our algorithm achieves zero energy cost, therefore, serves as a case study of perfectly imposing tree structures into vector space. An unknown Triple (h,r,x) will be predicted as true, when x’s n-ball is located in the r-subspace of h’s n-ball, following the same construction of known tails of h. The experiments are based on large datasets derived from the benchmark datasets WN11, FB13, and WN18. Our results show that the performance of the new method is related to the length of the type chain and the quality of pre-trained entityembeddings, and that performances of long chains with welltrained entity-embeddings outperform other methods in the literature. Source codes and datasets are located at https: //github.com/GnodIsNait/mushroom.

scholarly journals Android Apps Security Assessment using Sentiment Analysis Techniques: Comparative Study

2021 ◽  
Vol 15 (24) ◽  
pp. 123-133
Author(s):  
Abeer Aljumah ◽  
Amjad Altuwijri ◽  
Thekra Alsuhaibani ◽  
Afef Selmi ◽  
Nada Alruhaily
Keyword(s):  
Comparative Study ◽  
Sentiment Analysis ◽  
Security Assessment ◽  
Sensitive Data ◽  
User Reviews ◽  
Application Security ◽  
Analysis Techniques ◽  
Android Apps ◽  
Fake Reviews ◽  
Google Play

Considering that application security is an important aspect, especially nowadays with the increase in technology and the number of fraudsters. It should be noted that determining the security of an application is a difficult task, especially since most fraudsters have become skilled and professional at manipulating people and stealing their sensitive data. Therefore, we pay attention to trying to spot insecurity apps, by analyzing user feedback on the Google Play platform and using sentiment analysis to determine the apps level of security. As it is known, user reviews reflect their experiments and experiences in addition to their feelings and satisfaction with the application or not. But unfortunately, not all of these reviews are real, and as is known, the fake reviews do not reflect the sincerity of feelings, so we have been keen in our work to filter the reviews to be the result is accurate and correct. This study is useful for both users wanting to install android apps and for developers interested in app optimization.

scholarly journals Smartphone Apps About Crystal Methamphetamine (“Ice”): Systematic Search in App Stores and Assessment of Composition and Quality (Preprint)

2018 ◽  
Author(s):  
Cath Chapman ◽  
Katrina Elizabeth Champion ◽  
Louise Birrell ◽  
Hannah Deen ◽  
Mary-Ellen Brierley ◽  
...  
Keyword(s):  
English Language ◽  
Rating Scale ◽  
Smartphone Apps ◽  
Crystal Methamphetamine ◽  
Android Apps ◽  
Acceptable Quality ◽  
The Mean ◽  
Further Development ◽  
Google Play

BACKGROUND Amid considerable community concern about the prevalence and harms associated with the use of crystal methamphetamine (“ice”), the increased use of smartphones to access health information and a growing number of available smartphone apps related to crystal methamphetamine, no previous reviews have examined the content and quality of these apps. OBJECTIVE This study aims to systematically review existing apps in the iTunes and Google Play Stores to determine the existence, composition, and quality of educational smartphone apps about methamphetamines, including ice. METHODS The iTunes and Google Play Stores were systematically searched in April 2017 for iOS Apple and Android apps, respectively. English-language apps that provided educational content or information about methamphetamine were eligible for inclusion. Eligible apps were downloaded and independently evaluated for quality by 2 reviewers using the Mobile Application Rating Scale (MARS). RESULTS A total of 2205 apps were initially identified, of which 18 were eligible and rated using the MARS. The mean MARS quality total score for all rated apps was 3.0 (SD 0.6), indicating poor to acceptable quality. Overall, mean scores were the highest for functionality (mean 4.0, SD 0.5) and lowest for engagement (mean 2.3, SD 0.7). CONCLUSIONS This study demonstrates a shortage of high-quality educational and engaging smartphone apps specifically related to methamphetamine. The findings from this review highlight a need for further development of engaging and evidence-based apps that provide educational information about crystal methamphetamine.

Leveraging Fine-Grained Sentiment Analysis for Competitivity

2018 ◽  
Vol 17 (02) ◽  
pp. 1850018 ◽  
Author(s):  
Stephen Nabareseh ◽  
Eric Afful-Dadzie ◽  
Petr Klimek
Keyword(s):  
Social Media ◽  
Sentiment Analysis ◽  
Opinion Mining ◽  
Online Advertising ◽  
Fine Grained ◽  
Textual Data ◽  
Telecommunication Companies ◽  
Social Media Tools ◽  
Use Of Social Media

The surge in the use of social media tools by most businesses and corporate society for varied purposes cannot be over emphasised. The two top social media sites heavily patronised by businesses are Facebook and Twitter. For companies to harness the business potential of social media to increase competitive advantage, sentiments behind textual data of their customers, fans and competitors must be monitored and analysed with keen interest. This paper demonstrates how companies in the Telecommunication industry can understand consumer opinions, frustrations and satisfaction through opinion mining analyses and interpret customers’ textual data to enhance competitiveness. Sentiment analysis that classifies positive, negative and neutral sentiments of customers of the top three telecommunication companies in Ghana (MTN, Vodafone and Tigo) is studied. The proposed method extracts “intelligence” from the classified customers’ comments and compares it with responses from the companies. The results show how customer sentiments can be harnessed into successful online advertising projects. Companies can use the results to enhance their responsiveness to customer-centred, improve on the quality of their service, integrate social sentiments into PR plan, develop a strategy for social media marketing and leverage on the advantages of online advertising.

Convolutional Neural Network for Customer’s Opinion on Amazon Products

2019 ◽  
Vol 8 (3) ◽  
pp. 6634-6643 ◽  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Sentiment Analysis ◽  
Latent Dirichlet Allocation ◽  
Opinion Mining ◽  
Text Documents ◽  
Customer Churn ◽  
Learning Classifier ◽  
Review Spam

Opinion mining and sentiment analysis are valuable to extract the useful subjective information out of text documents. Predicting the customer’s opinion on amazon products has several benefits like reducing customer churn, agent monitoring, handling multiple customers, tracking overall customer satisfaction, quick escalations, and upselling opportunities. However, performing sentiment analysis is a challenging task for the researchers in order to find the users sentiments from the large datasets, because of its unstructured nature, slangs, misspells and abbreviations. To address this problem, a new proposed system is developed in this research study. Here, the proposed system comprises of four major phases; data collection, pre-processing, key word extraction, and classification. Initially, the input data were collected from the dataset: amazon customer review. After collecting the data, preprocessing was carried-out for enhancing the quality of collected data. The pre-processing phase comprises of three systems; lemmatization, review spam detection, and removal of stop-words and URLs. Then, an effective topic modelling approach Latent Dirichlet Allocation (LDA) along with modified Possibilistic Fuzzy C-Means (PFCM) was applied to extract the keywords and also helps in identifying the concerned topics. The extracted keywords were classified into three forms (positive, negative and neutral) by applying an effective machine learning classifier: Convolutional Neural Network (CNN). The experimental outcome showed that the proposed system enhanced the accuracy in sentiment analysis up to 6-20% related to the existing systems.

Evaluation of Persian language epilepsy-related mobile apps: A systematic review and quality assessment with a focus on content (Preprint)

2020 ◽  
Author(s):  
Mina Zibaei ◽  
Reza Khajouei
Keyword(s):  
Information Quality ◽  
Mobile Apps ◽  
Self Care ◽  
Keywords Epilepsy ◽  
Limited Health Literacy ◽  
Persian Language ◽  
The Mean ◽  
Limited Health ◽  
Google Play

BACKGROUND In Iran, around 0.05 of population suffer from epilepsy. Poorer health outcomes stem from limited health literacy. The use of mHealth, especially for educating patients in terms of self-care can be very effective. But the important thing is the content that is presented by apps, especially when unreliable or biased information can negatively affect the patient-doctor relationship, causing anxiety or stress. Also, usability of mHealth apps and their impact on behavior change are the other important issues that should be considered. OBJECTIVE The purpose of this study was to assess the quality of Persian language epilepsy-related mobile applications in terms of functionality and quality with a focus on content. METHODS The Persian equivalent of the keywords 'epilepsy' and 'seizure' were searched in the Google Play, Cafe Bazaar and IranApps app stores and the Persian language applications about epilepsy were extracted. These apps were evaluated by two trained reviewers independently using the uMARS scale and DISCERN instrument. Also apps’ prices and the number of installations were assessed. RESULTS A total of 659 applications were retrieved, 78 of which were epilepsy-related. After exclusion of non-Persian language and duplicate apps, there remained 11 relevant apps. The overall mean uMARS score was 2.8 out of 5 while six out of 11 apps (54%) scored higher than 3. The mean figures for the section-specific scores were as follows: engagement 2.2, functionality 4.0, aesthetics 3.3, and information 2.3. The overall DISCERN scores ranged from 26 to 40 out of 80, while the mean score was 34.5. The mean score of reliability was 18.5. CONCLUSIONS This study showed that the overall information quality of the epilepsy apps is poor. The most important missing characteristics of these apps include lack of functionalities for self-care, missing entry date, lack of details about additional sources and inexistence of the risks/benefits of each treatment. The findings suggest that more efforts should be made to develop evidence-based epilepsy-related apps to cover broader domains of self-care and behavioral change techniques.

App review of anxiety and depression chatbots and their self-care features (Preprint)

2020 ◽  
Author(s):  
Arfan Ahmed ◽  
Nashva ALi ◽  
Sarah Aziz ◽  
Alaa A Abd-Alrazaq ◽  
Asmaa Hassan ◽  
...  
Keyword(s):  
Mental Health ◽  
Meta Analysis ◽  
Self Care ◽  
Anxiety And Depression ◽  
Conversational Agents ◽  
Eligibility Criteria ◽  
On Demand ◽  
User Ratings ◽  
Google Play

BACKGROUND Anxiety and depression rates are at an all-time high along with other mental health disorders. Smartphone-based mental health chatbots or conversational agents can aid psychiatrists and replace some of the costly human based interaction and represent a unique opportunity to expand the availability and quality of mental health services and treatment. Regular up-to-date reviews will allow medics and individuals to recommend or use anxiety and depression related smartphone based chatbots with greater confidence. OBJECTIVE Assess the quality and characteristics of chatbots for anxiety and depression available on Android and iOS systems. METHODS A search was performed in the App Store and Google Play Store following the Preferred Reporting Items for Systematic reviews and Meta-Analysis (PRISMA) protocol to identify existing chatbots for anxiety and depression. Eligibility of the chatbots was assessed by two individuals based on predefined eligibility criteria. Meta-data of the included chatbots and their characteristics were extracted from their description and upon installation by 2 reviewers. Finally, chatbots quality information was assessed by following the mHONcode principles. RESULTS Although around 1000 anxiety and depression related chatbots exist, only a few (n=11) contained actual chatbots that could provide the user a real substitute for a human-human based interaction, even with today's Artificial Intelligence advancements, only one of these chatbots had voice as an input/output modality. Of the selected apps that contained chatbots all were clearly built with a therapeutic human substitute goal in mind. The majority had high user ratings and downloads highlighting the popularity of such chatbots and their promising future within the realm of anxiety and depression. CONCLUSIONS Anxiety and depression chatbot apps have the potential to increase the capacity of mental health self-care providing much needed assistance to professionals. In the current covid-19 pandemic, chatbots can also serve as a conversational companion with the potential of combating loneliness, especially in lockdowns where there is a lack of social interaction. Due to the ubiquitous nature of chatbots users can access them on-demand at the touch of a screen on ones’ smartphone. Self-care interventions are known to be effective and exist in various forms and some can be made available as chatbot features, such as assessment, mood tracking, medicine tracking, or simply providing conversation in times of loneliness.

Sign in / Sign up

Export Citation Format

Share Document