Classification Of Messages Research Articles

Nonverbal Communication as a Symbol of Love in Long Distance Relationship (LDR)

Communication is a form of interaction that humans do in conveying various forms of messages both verbally and nonverbally. In some cases, such as describing the expression of love and affection towards a partner, humans use nonverbal communication. Research on nonverbal communication as a symbol of love for long-distance partners in the midst of the COVID-19 pandemic was carried out using descriptive qualitative research methods. Data were obtained through in-depth interviews using a purposive sampling technique. There were 5 informants. The data analysis process went through the data collection stages. data reduction, data display and conclusions.. The results show that the classification of nonverbal messages in sign language can be represented by the use of emojis when exchanging messages. Furthermore, the language of action can be represented by how couples communicating while in their long distance relationship like exchanging messages, video calling, and so on. Finally, object language can be represented by giving surprises or gifts, exchanging photos, and so on. The conclusion of nonverbal communication as a symbol of affection for long-distance partners can be represented by 3 classifications of nonverbal messages, namely sign language, action language, and object language. The advice given can always maintain the warmth of the relationship even though you are in the middle of a long-distance relationship and better understand each other's love language.

Regionalized models for Spanish language variations based on Twitter.

Spanish is one of the most spoken languages in the world. Its proliferation comes with variations in written and spoken communication among different regions. Understanding language variations can help improve model performances on regional tasks, such as those involving figurative language and local context information. This manuscript presents and describes a set of regionalized resources for the Spanish language built on 4-year Twitter public messages geotagged in 26 Spanish-speaking countries. We introduce word embeddings based on FastText, language models based on BERT, and per-region sample corpora. We also provide a broad comparison among regions covering lexical and semantical similarities and examples of using regional resources on message classification tasks.

Realtime user ratings as a strategy for combatting misinformation: an experimental study

Because fact-checking takes time, verdicts are usually reached after a message has gone viral and interventions can have only limited effect. A new approach recently proposed in scholarship and piloted on online platforms is to harness the wisdom of the crowd by enabling recipients of an online message to attach veracity assessments to it. The intention is to allow poor initial crowd reception to temper belief in and further spread of misinformation. We study this approach by letting 4000 subjects in 80 experimental bipartisan communities sequentially rate the veracity of informational messages. We find that in well-mixed communities, the public display of earlier veracity ratings indeed enhances the correct classification of true and false messages by subsequent users. However, crowd intelligence backfires when false information is sequentially rated in ideologically segregated communities. This happens because early raters’ ideological bias, which is aligned with a message, influences later raters’ assessments away from the truth. These results suggest that network segregation poses an important problem for community misinformation detection systems that must be accounted for in the design of such systems.

Social Movement Sustainability on Social Media: An Analysis of the Women’s March Movement on Twitter

Social media has emerged as a powerful medium to organize and mobilize social movements. In particular, the connective action of social media builds associations and allows for the continuity of social movements. Yet there is a lack of research on how connective action emergent from social media messages sustains long-term social movements. Accordingly, in this study, we concentrate on Twitter messages related to Women’s March protests held in 2017, 2018, and 2019. Using an interpretive analysis followed by the topic modeling approach, we analyzed the tweets to identify the different types of messages associated with the movement. These messages were classified using a set of categories and subcategories. Furthermore, we conducted a temporal analysis of the message (sub)categories to understand how distinct messages allow movement continuity beyond a specific protest march. Results suggest that while most of the messages are used to motivate and mobilize individuals, the connective action tactics employed through messages sent before, during, and after the marches allowed Women’s March to become a broader and more persistent movement. We advance theoretical propositions to explain the sustainability of a long-term social movement on social media, exemplified through large-scale connective action that persists over time. In doing so, this study contributes to connective action research by providing message categorization that synthesizes the meaning of message content. The findings could help social movement organizers learn different ways to frame messages that resonate with broader social media users. Moreover, our approach to analyzing a large set of tweets might interest other qualitative researchers.

Characterization of the Mobile User Profile Based on Sentiments and Network Usage Attributes

Providing resources to meet user needs in futuristic mobile networks is still challenging since the network resources like spectrum and base stations do not increase in the same proportion as the accelerated growth of network traffic. Because of this, human/user behavior attributes can assist resource management in dealing with these challenges, which pick up aspects of how the user impacts the usage of mobile networks, such as network usage, the content of interest, urban mobility routines, social networks, and sentiment. A user profile is a combination of user/human behavior attributes. Such profiles are expected to be a knowledge for softwarization enablers to improve the management of future wireless networks fully. Nevertheless, the correlation between human sentiment and wireless and mobile network usage has not been deeply investigated in the literature about the mobile user profile. This work aims to define the user profile using a transfer learning approach for the sentiment classification of WhatsApp messages. A real-life experiment was conducted to collect users' attributes, namely the WhatsApp messages and network usage. A new data analysis methodology is proposed that consists of a frequent item-set pattern mining (FP-Growth) based on Association Rules, the Chi-squared statistical test, and descriptive statistics. This methodology assesses the correlation between sentiment and network usage in a profound way. Results show that the users participating in the experiment form three groups. The first group, with 55.6% of the users, contains users who present a strong relation between negative sentiment and low network usage and also a strong relation between positive sentiment and high network usage. The second group contains 25.9% of the users and is composed of userswho present a strong relation between positive sentiment and high network usage. The third group contains 18.5% of the users for whom the correlation between sentiment and network usage is still statistical significant, but the strength of this relation is much more weak then in the other two groups. Thus, 81.5% of the users (the first two groups) present a strong relation between user sentiment captured from WhatsApp messages and the network traffic generated by them.

Deep learning‐based smishing message identification using regular expression feature generation

AbstractThe increase in the number of undesired SMS termed smishing message and the data imbalance problem has generated a great demand for the development of more reliable anti‐spam filters. State of the art machine learning approaches are being employed to recognize and separate spam messages. Most recent studies target message classification by using numerous properties and features of the words but fail to consider the circumstantial features like long‐range dependencies between the words that are extremely important in identifying smishing messages. The idea is to develop an intelligent model that will distinguish between smishing messages and ham messages, by adopting a combined approach of regular expression (Regex), machine learning (ML) and deep learning (DL) models. Regex rules are generated using the dataset's spam messages for the purpose of refining the dataset. Support vector machine (SVM), Multinomial Naive Bayes and Random Forest are included under machine learning models and long short‐term memory (LSTM), bidirectional long short‐term memory (Bi‐LSTM), stacked LSTM and stacked Bi‐LSTM are included under deep learning models. The comparison between machine learning models and deep learning models is also carried out based on the performance evaluation parameters namely accuracy, precision, recall and F1 score of the models. It is observed that deep learning models perform better than machine learning models and the introduction of a regular expression to the dataset increases the efficiency of both the deep learning models and machine learning models.

Automatic Classification of Eyewitness Messages for Disaster Events Using Linguistic Rules and ML/AI Approaches

Emergency response systems require precise and accurate information about an incident to respond accordingly. An eyewitness report is one of the sources of such information. The research community has proposed diverse techniques to identify eyewitness messages from social media platforms. In our previous work, we created grammar rules by exploiting the language structure, linguistics, and word relations to automatically extract feature words to classify eyewitness messages for different disaster types. Our previous work adopted a manual classification technique and secured the maximum F-Score of 0.81, far less than the static dictionary-based approach with an F-Score of 0.92. In this work, we enhanced our work by adding more features and fine-tuning the Linguistic Rules to identify feature words related to Twitter Eyewitness messages for Disaster events, named as LR-TED approach. We used linguistic characteristics and labeled datasets to train several machine learning and deep learning classifiers for classifying eyewitness messages and secured a maximum F-score of 0.93. The proposed LR-TED can process millions of tweets in real-time and is scalable to diverse events and unseen content. In contrast, the static dictionary-based approaches require domain experts to create dictionaries of related words for all the identified features and disaster types. Additionally, LR-TED can be evaluated on different social media platforms to identify eyewitness reports for various disaster types in the future.

How Do Consumers Understand Food Processing? A Study on the Brazilian Population.

Food guides are official documents that guide consumers’ food choices. They inform the qualitative classification of food groups and messages on how to adopt a healthy diet. The classifications and nomenclatures adopted in these documents vary according to cultural, nutritional, and scientific criteria. This study aimed to evaluate the understanding of Brazilian consumers regarding food classification according to the Food Guide for the Brazilian Population (FGBP) concepts. An instrument was constructed to assess consumer understanding. It was named “Understanding of the Level of Processing of Food” (ULPF) and validated according to the concepts of constructs presented by psychometrics such as the Delphi methodology. The instrument was composed of 36 items approved by experts (concordance > 80% and with good internal consistency). A total of 2333 Brazilians from all regions participated in the study. The results suggest that food classification according to the level of processing was difficult for participants to understand. About 85% of them did not understand or did not know the definitions and classification of food and preparations according to food and science technology (FST) and the FGBP. More than 50% of the participants believed that it was easier to classify food according to food groups.

A novel approach for spam detection using horse herd optimization algorithm

Communication via email has expanded dramatically in recent decades due to its cost-effectiveness, convenience, speed, and utility for a variety of contexts, including social, scientific, cultural, political, authentication, and advertising applications. Spam is an email sent to a large number of individuals or organizations without the recipient's desire or request. It is increasingly becoming a harmful part of email traffic and can negatively affect the usability of email systems. Such emails consume network bandwidth as well as storage space, causing email systems to slow down, wasting time and effort scanning and eliminating enormous amounts of useless information. Spam is also used for distributing offensive and harmful content on the Internet. The objective of the current study was to develop a new method for email spam detection with high accuracy and a low error rate. There are several methods to recognize, detect, filter, categorize, and delete spam emails, and almost the majority of the proposed methods have some extent of error rate. None of the spam detection techniques, despite the optimizations performed, have been effective alone. A step in text mining and message classification is feature selection, and one of the best approaches for feature selection is the use of metaheuristic algorithms. This article introduces a new method for detecting spam using the Horse herd metaheuristic Optimization Algorithm (HOA). First, the continuous HOA was transformed into a discrete algorithm. The inputs of the resulting algorithm then became opposition-based and then converted to multiobjective. Finally, it was used for spam detection, which is a discrete and multiobjective problem. The evaluation results indicate that the proposed method performs better compared to other methods such as K-nearest neighbours-grey wolf optimisation, K-nearest neighbours, multilayer perceptron, support vector machine, and Naive Bayesian. The results show that the new multiobjective opposition-based binary horse herd optimizer, running on the UCI data set, has been more successful in the average selection size and classification accuracy compared with other standard metaheuristic methods. According to the findings, the proposed algorithm is substantially more accurate in detecting spam emails in the data set in comparison with other similar algorithms, and it shows lower computational complexity.

CAN Bus Messages Abnormal Detection Using Improved SVDD in Internet of Vehicles

Controller Area Network (CAN) bus anomaly detection on the Internet of Vehicle (IoV) is a topic of ongoing interest and increasing importance, particularly as IoV becomes commonplace. However, existing abnormal detection schemes are not ideal due to the lack of abnormal data in IoV and the difficulty of parsing the diverse message rules in existing vehicles. While single-classification of the SVDD (Support Vector Domain Description) algorithm can detect abnormalities only with normal message information, the approach has a high rate of false negatives when deployed directly in the in-vehicle network environment. In addition, the real-time data generation (e.g., IoV messages) compounds the challenge of designing effective detection approaches. Therefore, this paper proposes a mechanism for car networking message classification for a broad range of data, and establishes a weak model for many simple redundant data in the vehicle intranet. The detection can reduce the time and computation costs of detection while ensuring accuracy. Then, this paper proposes two improved SVDD schemes: M-SVDD scheme which adds the Markov chain to detect time-related messages; G-SVDD scheme which maps the kernel function to the Gaussian kernel function to reduce the redundant area of the model and the false-negative rate. The experimental results show that our proposed schemes have higher accuracy, recall rate and fewer computation overhead.

ANALYSIS OF REPORTED FOOD FRAUD IN THE GLOBAL BEEF SUPPLY CHAIN 2000-2020

Relevant food notifications published under the Rapid Alert System for Food and Feed (RASFF) for 2000-2020 were selected and analyzed to determine their overall formula. Fraud/counterfeiting was categorized according to the type of fraud, its location in the food production chain, the reporting country, and the origin of the food. "Adulteration" was the most common type of fraud in the beef industry; it accounted for 70% of all documented reports. According to the classification of supply chain messages, 59% of all cases were attributed to secondary processing, of which 83% were cases of "adulteration". The most common counterfeiting practices included products manufactured/packaged in non-approved areas, without appropriate control or documentation, products with fraudulent health certificates, and substitution of meat types or the addition of veterinary medicines.

The Phenomenon of Responsibility in the Structure of Russians' Concepts about Professional Activities

The paper analyzes the state of research on the phenomenon of responsibility in the scientific literature and its place within the framework of psychological knowledge, including in the context of professional and entrepreneurial activities. It is shown that the macropsychological analysis of the attitude of Russians to the social aspects of responsibility as a psychological phenomenon is an actual, but little studied problem. The study is aimed at identifying the structural and content characteristics of social network users' perceptions of professional responsibility as a unique (not identical) phenomenon to other types of responsibility. In accordance with the stated goal, there is an appeal to neural network automated methods for analyzing large amounts of information according to semantic, frequency and emotional criteria. The general classification of messages is made in the expert mode. The results of the study made it possible to formulate a number of main conclusions: responsibility is perceived as an inalienable component of professional activity; the greatest responsibility is attributed to professionals responsible for the well-being of others; the more people are in the sphere of distribution of the powers of a professional, the higher the level of responsibility attributed to him; professional responsibility gives rise to a wide range of different experiences, in the structure of which a dishonest attitude to the fulfillment of one's obligations causes extremely negative assessments. The paper reveals the principles of personalization and depersonalization of responsibility. In the future, an analysis of similar ideas of residents of other countries is proposed.

Identification of atypical behavior of bank employees when using e-mail to prevent information leakages

The article presents the results of using machine learning methods to identify atypical behavior of bank employees when using e-mail. A feature space is formed that characterizes the behavior of e-mail users. The objects were previously clustered using the density-based spatial clustering of applications with noise (DBSCAN) and the fuzzy logic elements. The objects were marked using the inbuilt business rules, and the training sample was formed in the absence of marked data. The most informative features are selected, and a model of classification of e-mail users by the type of their behavior is constructed. A feature space is formed that defines the characteristics of a particular message to identify messages that are the information security incidents. Preliminary data processing was performed by removing the duplicates and encoding the categorical variables. A model of messages classification is constructed. The best combination of the machine learning method and the feature selection algorithm was determined using quality metrics. The constructed models allow specialists of cybersecurity departments of banks to identify employees with abnormal behavior and possibly involved in information leaks. A software tool in Python was developed that makes it easier to identify the final status of a message by partially replacing its manual detection for an automatic one.

ReapIoT: Reliable, Energy-Aware Network Protocol for Large-Scale Internet-of-Things (IoT) Applications

A new era is emerging where buildings, vehicles, factories, and appliances, among many other entities will communicate with each other over the Internet, with limited or no human interaction. Collectively known as the Internet of Things (IoT), these systems share a common technology foundation. They are built on wireless communication between stationary or mobile large-scale electronic sensor and actuator networks. For the vast majority of IoT applications, energy-efficient operations are a critical requirement since they will use battery-powered devices. Another requirement is communication reliability, due to unattended network operations. We introduce ReapIoT, reliable energy-aware protocol for IoT WSNs. ReapIoT is an energy-efficient network communication protocol that considers reliability as a design parameter and as a constraint. The protocol introduces message classification based on reliability. This is used to implement new energy saving techniques. The protocol also introduces the individualized link power settings algorithm, and the link rating parameter. They are used to optimize the network clusters formation and for intracluster communication, under reliability constraint. Consequently, the protocol optimizes energy consumption while providing a reliable data delivery network.

SMS CLASSIFICATION: CONJOINT ANALYSIS OF MULTINOMIAL NAIVE BAYES APPLICATION

Nowadays there are ham and spam messages that are sent to the users via SMS. The aim of this article is to show how machine learning and text processing technologies can be used in order to predict the trustworthiness of SMS messages. The data we are going to use is collected from Kaggle. This study is very important because it helps us to understand how machine learning and text processing can be used in order to predict message trustworthiness. At the time of writing this article, there was not an article explaining how this can be done using the Multinomial Naive Bayes algorithm. The methodology we used in this article consists of dataset collection, data cleaning, data analysis, text preparation, and training model. This will be seen in the methodology section in great detail. At the end of this article, we will show to u the accuracy that we have got when implementing a Multinomial Naive Bayes algorithm for the classification of SMS messages. This study was quite beneficial because anyone can see how Multinomial Naive Bayes algorithm usage can be beneficial in order to predict the trustworthiness of SMS messages.

Geographic context-aware text mining: enhance social media message classification for situational awareness by integrating spatial and temporal features

ABSTRACT To find disaster relevant social media messages, current approaches utilize natural language processing methods or machine learning algorithms relying on text only, which have not been perfected due to the variability and uncertainty in the language used on social media and ignoring the geographic context of the messages when posted. Meanwhile, a disaster relevant social media message is highly sensitive to its posting location and time. However, limited studies exist to explore what spatial features and the extent of how temporal, and especially spatial features can aid text classification. This paper proposes a geographic context-aware text mining method to incorporate spatial and temporal information derived from social media and authoritative datasets, along with the text information, for classifying disaster relevant social media posts. This work designed and demonstrated how diverse types of spatial and temporal features can be derived from spatial data, and then used to enhance text mining. The deep learning-based method and commonly used machine learning algorithms, assessed the accuracy of the enhanced text-mining method. The performance results of different classification models generated by various combinations of textual, spatial, and temporal features indicate that additional spatial and temporal features help improve the overall accuracy of the classification.

Understanding environmental tweets of for-profits and nonprofits and their effects on user responses

PurposeOrganizations are communicating with the public about their thoughts and behaviors relevant to the environment via social networking sites. The purpose of this paper is to explore for-profit and nonprofit organizations' Twitter messages to understand their environment-related messages and their influences on the publics' responses.Design/methodology/approachThis study conducted a content analysis adopting four message classification systems: environmental message orientation, message specificity, message framing, and environmental issue. Guided by attribution theory, this study also explored how the organization's environmental messages influence social media (Twitter) user responses, likes, retweets, and replies.FindingsThe analysis showed that for-profits' messages tend to discuss their green products and manufacturing processes with specific numeric evidence, while nonprofits are disposed to describe a severely degraded environment. In addition, the study revealed that tweets yield a high number of likes and replies when the organizations are for-profits and the messages emphasize green products.Research limitations/implicationsThe findings of this study showed that the green message categorization systems are applicable to the social media context. But, this study focused on Twitter only. Future studies need to examine various social media platforms.Practical implicationsThe study findings recommend communication practitioners use substantive green messages highlighting actual pro-environmental performances. Also, practitioners might need to make a linkage between the discussed environmental issue and the organization (e.g. a water issue by a wildlife-related nonprofit, an energy issue by a home appliance manufacturer, an air pollution issue by a bicycle company). In addition, regarding the message specificity, infographics can be present specific information that audiences can readily understand because it is described visually.Originality/valueScholars investigated environmental messages in advertising and cautioned that environmental messages that are not substantive or specific can cause audiences to perceive the messages as greenwashing. However, these previous studies focused on conventional media, and they have not been replicated in the age of social media. Thus, it is important to explore the current status of organizational environmental messages on social media.

Automatic Subject Classification of Public Messages in E-government Affairs

Public messages on the Internet political inquiry platform rely on manual classification, which has the problems of heavy workload, low efficiency, and high error rate. A Bi-directional long short-term memory (Bi-LSTM) network model based on attention mechanism was proposed in this paper to realize the automatic classification of public messages. Considering the network political inquiry data set provided by the BdRace platform as samples, the Bi-LSTM algorithm is used to strengthen the correlation between the messages before and after the training process, and the semantic attention to important text features is strengthened in combination with the characteristics of attention mechanism. Feature weights are integrated through the full connection layer to carry out classification calculations. The experimental results show that the F1 value of the message classification model proposed here reaches 0.886 and 0.862, respectively, in the data set of long text and short text. Compared with three algorithms of long short-term memory (LSTM), logistic regression, and naive Bayesian, the Bi-LSTM model can achieve better results in the automatic classification of public message subjects.

SM‐Detector: A security model based on BERT to detect SMiShing messages in mobile environments

SummaryThe growing use of SMS by businesses to communicate with their customers has made attackers more interested in smishing attacks. Smishing is a security attack that involves sending a fake SMS message in order to steal the personal credentials of mobile users. This kind of attack has become a serious cyber‐security issue and has caused great financial losses for both people and businesses. In this article we propose a hybrid security model called “SM‐Detector” aiming to detect smishing messages in mobile environments. To increase the efficiency of “SM‐Detector,” we have combined three different detection methods: (i) identification of malicious URLs, (ii) identification of suspected words, phone numbers and emails with regular expression analysis, and (iii) classification of messages using BERT‐based algorithms to distinguish spam messages. “SM‐Detector” also includes a mobile application allowing the user to check their SMS and report smishing messages. Its strength is that it can deal with mixed text messages written in Arabic or English. The experimental evaluation conducted on English and Arabic datasets showed a remarkable accuracy of 99.63%.

Automatic Content Analysis of Online Discussions for Cognitive Presence: A Study of the Generalizability Across Educational Contexts

This article investigates the impact of educational contexts on automatic classification of online discussion messages according to cognitive presence, an essential construct of the community of inquiry model. In particular, the work reported in the article analyzed online discussion messages written in Brazilian Portuguese from two different courses that were from different subject areas (biology and technology) and had different teaching presence in the online discussions. The study explored a set of 127 features of online discussion messages and a random forest classifier to automatically recognize the phases of the cognitive presence in online discussion messages. The results showed that the classifier achieved better performance when applied to the entire dataset. It reveals that when a classifier is created for a specific course it is not generic enough to be applied to a course from a different field of knowledge. The results also showed the importance of the features that were predictive of the phases of the cognitive presence in the educational context. Based on the findings of this study, future work should adopt the same feature set as used in the current study, but it should train the classifier of the cognitive presence on datasets in subject areas related to the topic of the discussions.