textual content
Recently Published Documents





Complexity ◽  
2022 ◽  
Vol 2022 ◽  
pp. 1-12
Muhammad Zubair Asghar ◽  
Adidah Lajis ◽  
Muhammad Mansoor Alam ◽  
Mohd Khairil Rahmat ◽  
Haidawati Mohamad Nasir ◽  

Emotion-based sentimental analysis has recently received a lot of interest, with an emphasis on automated identification of user behavior, such as emotional expressions, based on online social media texts. However, the majority of the prior attempts are based on traditional procedures that are insufficient to provide promising outcomes. In this study, we categorize emotional sentiments by recognizing them in the text. For that purpose, we present a deep learning model, bidirectional long-term short-term memory (BiLSMT), for emotion recognition that takes into account five main emotions (Joy, Sadness, Fear, Shame, Guilt). We use our experimental assessments on the emotion dataset to accomplish the emotion categorization job. The datasets were evaluated and the findings revealed that, when compared to state-of-the-art methodologies, the proposed model can successfully categorize user emotions into several classifications. Finally, we assess the efficacy of our strategy using statistical analysis. This research’s findings help firms to apply best practices in the selection, management, and optimization of policies, services, and product information.

2022 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Kyongseok Kim ◽  
Hyang-Sook Kim

Purpose The purpose of this study is to test the visual superiority effect in a verisimilar scenario that an industry association seeks to manipulate consumers using a visual element in its ad while providing an ostensibly balanced claim about the potential health effects of stevia. Design/methodology/approach Two experiments were conducted. In Study 1, an online experiment was conducted with a sample of 112 adult consumers using a two-group (headline frame type: gain vs loss), post-test only design with additional planned analysis of an individual difference (i.e. regulatory focus). In Study 2, another online experiment was implemented with a sample of 175 adults using a 2 (headline frame type: gain vs loss) × 2 (image valence: positive vs negative) between-subjects design with additional planned analysis of regulatory focus. The hypotheses were tested by running the PROCESS macro on SPSS. Findings The results showed that when exposed to the advertising message designed to elicit uncertainty, participants relied more on the visual than the textual content (i.e. framed headline and body text) in forming attitude toward the behavior (i.e. consuming stevia). Analysis of cognitive responses also revealed that those who received the stimulus ad with an image added (Study 2) generated significantly fewer thoughts related to the textual content of the ad than those who received the ad with no image (Study 1). Originality/value This study represents one of the earliest experimental inquiries into the visual superiority effect in an advertising context. While earlier studies have tended to rely on dual-processing models to test the effects of advertising stimuli featuring both textual and visual elements, the findings of this study (e.g. visual content overwhelmed its textual counterpart in producing persuasive effects) somewhat contradict the premise of dual-processing models.

2022 ◽  
Vol 27 ◽  
pp. 980-994
Modipa Mmakwena ◽  
Motseki Moses

Covid 19 in South Africa created opportunity for criminals to enrich themselves at the expense of the poor. Public and private sector officials benefited due to irregular tenders and overpricing of personal protective equipments in South Africa as reported on media platforms. This article explores opportunistic crimes associated with Covid 19 and their impact on the fight against the pandemic. This qualitative article adopted a non-empirical research design: Systematic review, indirect observation schedules to identify and describe available research literature ‘using systematic and explicit accountable methods and pre-specified formalised tools for searching and integrating literature. The data was collected from January-July 2021. The collected data was analysed through inductive textual content analysis. Findings revealed that public officials benefited from irregular PPE tenders as well as friends and families of politicians. The findings further indicate that billions of Rands were looted from funds which were meant to fight Covid 19 in South Africa. Lastly the findings show that law enforcement agencies are not effective in dealing with cases of Covid 19 crimes. Based on the findings, the following recommendations were developed: Law enforcement agencies should be equipped with resources to deal with Covid 19 crimes and ensure successful prosecution of those crimes, Competition Commission should investigate the companies which benefited from irregular tenders and overpricing of PPE’s so that they could be held accountable. Public participation should be strengthened to combat crime.

2022 ◽  
pp. 188-205
Erkan Çiçek ◽  
Uğur Gündüz

Social media has been in our lives so much lately that it is an undeniable fact that global pandemics, which constitute an important part of our lives, are also affected by these networks and that they exist in these networks and share the users. The purpose of making this hashtag analysis is to reveal the difference in discourse and language while analyzing Twitter data and to evaluate the effects of a global pandemic crisis on language, message, and crisis management with social media data. This form of analysis is typically completed through amassing textual content data then investigating the “sentiment” conveyed. Within the scope of the study, 11,300 Twitter messages posted with the #stayhome hashtag between 30 May 2020 and 6 June 2020 were examined. The impact and reliability of social media in disaster management could be questioned by carrying out a content analysis based totally on the semantic analysis of the messages given on the Twitter posts with the phrases and frequencies used.

2022 ◽  
Vol 131 ◽  
pp. 02005
Kristiina Sepp ◽  
Kadi Lubi ◽  
Hedvig Rass ◽  
Daisy Volmer

The spread of COVID-19 outbreak in 2020 had significant impact on the functioning of the existing healthcare system and required fast adaption to new circumstances for continuing with daily practices. Community pharmacists shared responsibility of ensuring supply of medicines and medical devices, educating people on health related issues, providing pharmaceutical care etc. The aim of this study was to understand how the provision of community pharmacy services changed during the first wave of COVID-19 pandemic in spring of 2020 in Estonia. Qualitative in-depth semi-structured interviews were conducted. Recorded interviews with community pharmacists (n = 21) and experts (n =10) were transcribed verbatim and a systematic text condensation method for textual content analysis was performed. The findings indicated that a number of changes took place in provision of community pharmacy services to assure continuity in providing high-quality pharmacy services in crisis, including addressing difficulties in the supply of medicines; at the same time, to acquire new knowledge for counselling health related topics and personal protective equipment, and to provide psychological support to people in stress. Pandemic had an impact on the content and structure of traditional community pharmacy services in Estonia. The need for expanded professional role of pharmacists was clearly expressed in an emergency situation.

2021 ◽  
Vol 38 (6) ◽  
pp. 1809-1817
Praveen Kumar Yechuri ◽  
Suguna Ramadass

The advent of social networking and the internet has resulted in a huge shift in how consumers express their loyalty and where firms acquire a reputation. Customers and businesses frequently leave comments, and entrepreneurs do the same. These write-ups may be useful to those with the ability to analyse them. However, analysing textual content without the use of computers and the associated tools is time-consuming and difficult. The goal of Sentiment Analysis (SA) is to discover client feedback, points of view, or complaints that describe the product in a more negative or optimistic light. You can expect this to be a result based on this data if you merely read and assess feedback or examine ratings. There was a time when only the use of standard techniques, such as linear regression and Support Vector Machines (SVM), was effective for the task of automatically discovering knowledge from written explanations, but the older approaches have now been mostly replaced by deep neural networks, and deep learning has gotten the job done. Convolution and compressing RNNs are useful for tasks like machine translation, caption creation, and language modelling, however they suffer from gradient disappearance or explosion issues with large words. This research uses a deep learning RNN for movie review sentiment prediction that is quite comparable to Long Short-Term Memory networks. A LSTM model was well suited for modelling long sequential data. Generally, sentence vectorization approaches are used to overcome the inconsistency of sentence form. We made an attempt to look into the effect of hyper parameters like dropout of layers, activation functions and we also tested the model with different neural network settings and showed results that have been presented in the various ways to take the data into account. IMDB is the official movie database which serves as the basis for all of the experimental studies in the proposed model.

Lingyun Mi ◽  
Tianwen Jia ◽  
Yang Yang ◽  
Lulu Jiang ◽  
Bangjun Wang ◽  

Evaluating the effectiveness of ecological civilization policies is the basis from which policymakers can optimize policies. From the perspective of the overall effectiveness of regional policies, and taking Jiangsu Province as an example, this study constructed a quantitative evaluation model of eco-civilization policy text and an eco-civilization evaluation index system. Using these tools, this paper evaluates the effectiveness of 53 ecological civilization policies issued by Jiangsu Province during 2004–2019 to promote the construction of ecological civilization in the four fields of resource utilization, environmental protection, economic development, and social life. There are three key findings. (1) During the period of 2004–2019, the effectiveness of the textual content of ecological civilization policies in Jiangsu Province generally showed a fluctuating upward trend. (2) The construction effectiveness indexes of the four fields of eco-civilization all showed a growth trend, but the construction effect varied greatly. The index of economic development had grown rapidly, while environmental protection had grown slowly. (3) Ecological civilization policies in Jiangsu Province were effective in promoting the construction of ecological civilization. However, the effects of different policy dimensions on ecological civilization development in the four fields were significantly different. Finally, based on these results, powerful recommendations are provided for the optimization of eco-civilization policies in Jiangsu Province. Moreover, Jiangsu is the first province in China to launch a provincial-level ecological civilization construction plan. Its policy optimization to promote ecological civilization construction can also provide an example and realistic basis for reference for the construction of eco-civilization in other provinces in China.

Harald Stiff ◽  
Fredrik Johansson

AbstractModern neural language models can be used by malicious actors to automatically produce textual content looking as it has been written by genuine human users. Due to progress in the controllability of computer-generated text, there is a risk that state-sponsored actors may start using such methods for conducting large-scale information operations. Various detection algorithms have been suggested in the research literature to identify texts produced by language model-based generators, but these are often mainly evaluated on test data from the same distribution as they have been trained on. We evaluate promising Transformer-based detection algorithms in a large variety of experiments involving both in-distribution and out-of-distribution test data, as well as evaluation on more realistic in-the-wild data. It is shown that the generalizability of the detectors can be questioned, especially when applied to short social media posts. Moreover, the best performing (RoBERTa-based) detector is shown to be non-robust also to basic adversarial attacks, illustrating how easy it is for malicious actors to avoid detection by the current state-of-the-art detection algorithms.

2021 ◽  
Vol 72 (06) ◽  
pp. 639-644

Online reviews have emerged as an essential information source for online clothing purchasing behaviour. It is thus paramount for marketers to understand what makes online clothing review helpful to consumers. This research primarily aims to examine the relationship between review textual content factors and review helpfulness in the context of online clothing purchasing. Experiments on review concreteness (concrete or abstract), review variance (consistent or inconsistent) and review valence (positive or negative), between participants were conducted to explore the interaction effect. The findings suggest that online clothing review concreteness, variance and valence are significant factors affecting review helpfulness. Additionally, this study’s findings show that abstract review, negatively review and inconsistent review has a stronger effect on online clothing review helpfulness than concrete review, positively review and consistent review. The findings will help customers to write better clothing reviews, help retailers to manage their websites intelligently and aid customers in their product purchasing decisions.

2021 ◽  
Miriam Alzate Barricarte

This doctoral thesis studies various aspects related to a specific type of electronic word of mouth, also referred to as eWOM, which are online consumer reviews. On the one hand, this thesis studies how certain non-textual and textual characteristics of online reviews, together with the visibility of those reviews, influence various types of consumer behaviour, specifically the adoption of information and the purchasing behaviour. On the other hand, this research studies the textual content of online reviews to study the brand positioning and brand segmentation, and to analyse the positioning and associations with products. Prior to the empirical analysis, the literature on information processing, decision-making literature, branding and text mining are mainly reviewed.

Sign in / Sign up

Export Citation Format

Share Document