Search results

Normalization is an important step in all the natural language processing applications that are handling social media text. The text from social media poses a different kind of problems that are not present in regular text. Recently, a considerable amount of work has been done in this direction, but mostly in the English language. People who do not speak English code mixed the text with their native language and posted text on social media using the Roman script. This kind of text further aggravates the problem of normalizing. This paper aims to discuss the concept of normalization with respect to code-mixed social media text, and a model has been proposed to normalize such text.

The system is divided into two phases – candidate generation and most probable sentence selection. Candidate generation task is treated as machine translation task where the Roman text is treated as source language and Gurmukhi text is treated as the target language. Character-based translation system has been proposed to generate candidate tokens. Once candidates are generated, the second phase uses the beam search method for selecting the most probable sentence based on hidden Markov model.

Character error rate (CER) and bilingual evaluation understudy (BLEU) score are reported. The proposed system has been compared with Akhar software and RB\_R2G system, which are also capable of transliterating Roman text to Gurmukhi. The performance of the system outperforms Akhar software. The CER and BLEU scores are 0.268121 and 0.6807939, respectively, for ill-formed text.

It was observed that the system produces dialectical variations of a word or the word with minor errors like diacritic missing. Spell checker can improve the output of the system by correcting these minor errors. Extensive experimentation is needed for optimizing language identifier, which will further help in improving the output. The language model also seeks further exploration. Inclusion of wider context, particularly from social media text, is an important area that deserves further investigation.

The practical implications of this study are: (1) development of parallel dataset containing Roman and Gurmukhi text; (2) development of dataset annotated with language tag; (3) development of the normalizing system, which is first of its kind and proposes translation based solution for normalizing noisy social media text from Roman to Gurmukhi. It can be extended for any pair of scripts. (4) The proposed system can be used for better analysis of social media text. Theoretically, our study helps in better understanding of text normalization in social media context and opens the doors for further research in multilingual social media text normalization.

Existing research work focus on normalizing monolingual text. This study contributes towards the development of a normalization system for multilingual text.

Despite the extensive academic interest in social media sentiment for financial fields, multimodal data in the stock market has been neglected. The purpose of this paper is to explore the influence of multimodal social media data on stock performance, and investigate the underlying mechanism of two forms of social media data, i.e. text and pictures.

This research employs panel vector autoregressive models to quantify the effect of the sentiment derived from two modalities in social media, i.e. text information and picture information. Through the models, the authors examine the short-term and long-term associations between social media sentiment and stock performance, measured by three metrics. Specifically, the authors design an enhanced sentiment analysis method, integrating random walk and word embeddings through Global Vectors for Word Representation (GloVe), to construct a domain-specific lexicon and apply it to textual sentiment analysis. Secondly, the authors exploit a deep learning framework based on convolutional neural networks to analyze the sentiment in picture data.

The empirical results derived from vector autoregressive models reveal that both measures of the sentiment extracted from textual information and pictorial information in social media are significant leading indicators of stock performance. Moreover, pictorial information and textual information have similar relationships with stock performance.

To the best of the authors’ knowledge, this is the first study that incorporates multimodal social media data for sentiment analysis, which is valuable in understanding pictures of social media data. The study offers significant implications for researchers and practitioners. This research informs researchers on the attention of multimodal social media data. The study’s findings provide some managerial recommendations, e.g. watching not only words but also pictures in social media.

This study aimed to present the methodology of the text data analysis to establish marketing strategies for fintech companies in a practical way. Specifically, the methodology was presented to convert customers' review data, which consisted of the text data (unstructured data), to the numerical data (structured data) by using a text mining algorithm “Global Vectors for Word Representation,” abbreviated as “GloVe”; additionally, the authors presented the methodology to deploy the numerical data for marketing strategies with eliminate-reduce-raise-create (ERRC) value factor analytics.

First, the authors defined the background, features and contents of fintech services based on a review of related literature review. Additionally, they examined business strategies, the importance of social media for fintech services and fintech technology trends based on the literature review. Next, they analyzed the similarity between fintech-related keywords, which represent the trends in fintech services, and the text data related to fintech corporations and their services posted on Facebook and Twitter, which are two of the most popular social media globally, during the period 2017–2019. The similarity was then quantified and categorized in terms of the representative global fintech companies and the status of each fintech service sector. Furthermore, the similarity was visualized, and value elements were rebuilt using ERRC strategy analytics.

This study is meaningful in that it quantifies the degree of similarity between customers' responses, experiences and expectations regarding the rapidly growing global fintech firms' services and trends in fintech services.

This study suggests a practical way to apply in business by providing a method for transforming unstructured text data into structured numerical data it is measurable. It is expected that this study can be used as the basis for exploring sustainable development strategies for the fintech industry.

Drawing on the theoretical domain of speech act theory (SAT) and a discussion of its suitability for setting the agenda for social media research, this study aims to explore a range of research directions that are both relevant and conceptually robust, to stimulate the advancement of knowledge and understanding of online verbatim data.

Examining previously published cross-disciplinary research, the study identifies how recent conceptual and empirical advances in SAT may further guide the development of text analytics in a social media context.

Decoding content and function word use in customers’ social media communication can enhance the efficiency of determining potential impacts of customer reviews, sentiment strength, the quality of contributions in social media, customers’ socialization perceptions in online communities and deceptive messages.

Considering the variety of managerial demand, increasing and diverging social media formats, expanding archives, rapid development of software tools and fast-paced market changes, this study provides an urgently needed, theory-driven, coherent research agenda to guide the conceptual development of text analytics in a social media context.

Following the hierarchy-of-effects model, this study aims to propose a two-step process framework to investigate social media post efficacy via attraction and likes.

The study analyzes 113,785 social media posts from 126 WeChat official accounts to explore how external (headline features and account type) and internal (content features and media type) features impact social media post attractions and likes, respectively.

The antecedents of post attraction differ from those of post likes. First, headline features (punctuation, length, sentiment and lexical density) and account type significantly influence social media post attraction. Second, content features (depth, tone, domain specificity, lexical density and readability) and media type affect social media post likes.

First, this study considers online user engagement as a two-step process regarding social media posts and explores different influencing factors. Second, the study constructs new variables (account type and domain specificity) in each stage of the two-step process model.

In the age of social media, when publishers are vying for consumer attention, click-baits have become very common. Not only viral websites but also mainstream publishers, such as news channels, use click-baits for generating traffic. Therefore, click-bait detection and prediction of click-bait virality have become important challenges for social media platforms to keep the platform click-bait free and give a better user experience. The purpose of this study is to try exploring how the contents of the social media posts and the article can be used to explain and predict social media posts and the virality of a click-bait.

This study has used 17,745 tweets from Twitter with 4,370 click-baits from top 27 publishers and applied econometric along with machine learning methods to explain and predict click-baitiness and click-bait virality.

This study finds that language formality, readability, sentiment scores and proper noun usage of social media posts and various parts of the target article plays differential and important roles in click-baitiness and click-bait virality.

The paper contributes toward the literature of dark behavior in social media at large and click-bait prediction and explanation in particular. It focuses on the differential roles of the social media post, the article shared and the source in explaining click-baitiness and click-bait virality via psycho-linguistic framework. The paper also provides explanability to the econometric and machine learning predictive models, thus performing methodological contribution too.

The paper helps social media managers create a mechanism to detect click-baits and also predict which ones of them can become viral so that corrective measures can be taken.

To the best of the authors’ knowledge, this is one of the first papers which focus on both explaining and predicting click-baitiness and click-bait virality.

The purpose of this study is to document how a traditional residential neighborhood, Ihwa village in Seoul, South Korea, is transformed into a tourist attraction and demonstrate the complexity of the overtourism phenomenon and the multifaceted conflicts among stakeholders that emerged in the course of urban transformation. Particularly, the study explores how tourism growth, urban transformation and overtourism are intertwined with each other and how the role of social media and media contributed to tourism growth and the transformation of an urban neighborhood.

The study conducted text analytics (a big data analysis) using personal blogs and news articles. Our data for text analytics was defined to retrieve all news articles and blogs existent in the NAVER portal, the largest Korean portal and search engine, for the period between January 1, 2006, and December 31, 2018. The data was collected using a web crawling program, TEXTOM version 3.0.

Text analysis of blog entries and news articles suggests that each medium has its unique role and domain to play. While the news media contributed to the initial surge of interest in Ihwa village, genuine growth of tourism in Ihwa village seems to be attributed to social media. Texts that appeared in blogs strongly indicated that people used their blogs to share their trip experiences, which can be subsequently assumed that blogs had an influential role in promoting a small place like Ihwa mural village, while news articles tended to highlight negative or unusual events occurred in Ihwa village. The study also addressed the multifaceted nature of the conflicts that were inherent in the issue of urban regeneration and how those conflicts were developed and manifested in the process of touristification and overtourism in Ihwa village. As touristification can manifest in various forms in different places, the case of Ihwa village demonstrates a unique development of touristification; private tourism companies or tourism agencies did not initiate or intend to cause tourism gentrification. Rather, touristification is a byproduct of urban revitalization through public art and is a result of interplay between the local government’s interest, social media and new tourist demand.

Text analytics using big data have rarely been attempted to understand the role of social media in relation to tourism growth and touristification of an urban tourism place. This study advances the literature by applying big data analysis to user-generated content in blogs. The study also contributes to the deeper understanding of a different developmental pattern of touristification in an urban tourism place as well as the complexity of the overtourism phenomenon and the multifaceted conflicts among stakeholders.

This study explores the levels of Facebook engagement of the two largest Europe-based shipping lines, Maersk and Mediterranean Shipping Company (MSC), to discover the marketing orientation of the topics advertised and to ascertain whether they tend to be about brand recognition, new transport services, or value propositions for stakeholders.

The Facebook posts of Maersk and MSC were analysed using social media text mining and social network analysis (SNA); in- and out-degree centrality analysis was performed to determine the key terms in their posts. NetMiner software was used to collect the respective data on Maersk and MSC. The inquiry period was set between May 2020 and February 2021.

The results indicated a divergence in their post contents, with higher engagement and a wider, more active follower base for MSC than for Maersk. Maersk primarily posts about logistics services and supply chain solutions. MSC communicates about new and large container vessels. Both companies seek greater brand recognition and information sharing through social media.

These results can be used by the stakeholders to evaluate whether Maersk and MSC truly deliver on their respective value propositions communicated online through their social media engagement. It can also help Maersk and MSC gauge the level of effectiveness of their communication with stakeholders and modify their digital engagement strategy accordingly.

This paper aims to equip professionals and researchers in the fields of advertising, branding, public relations, marketing communications, social media analytics and marketing with a simple, effective and dynamic means of evaluating consumer behavioural sentiments and engagement through Arabic language and script, in vivo.

Using quantitative and qualitative situational linguistic analyses of Classical Arabic, found in Quranic and religious texts scripts; Modern Standard Arabic, which is commonly used in formal Arabic channels; and dialectical Arabic, which varies hugely from one Arabic country to another: this study analyses rich marketing and consumer messages (tweets) – as a basis for developing an Arabic language social media methodological tool.

Despite the popularity of Arabic language communication on social media platforms across geographies, currently, comprehensive language processing toolkits for analysing Arabic social media conversations have limitations and require further development. Furthermore, due to its unique morphology, developing text understanding capabilities specific to the Arabic language poses challenges.

This study demonstrates the application and effectiveness of the proposed methodology on a random sample of Twitter data from Arabic-speaking regions. Furthermore, as Arabic is the language of Islam, the study is of particular importance to Islamic and Muslim geographies, markets and marketing.

The findings suggest that the proposed methodology has a wider potential beyond the data set and health-care sector analysed, and therefore, can be applied to further markets, social media platforms and consumer segments.

To remedy these gaps, this study presents a new methodology and analytical approach to investigating Arabic language social media conversations, which brings together a multidisciplinary knowledge of technology, data science and marketing communications.

The COVID-19 epidemic has brought attention to the variables that influence the mental health of health workers who are entrusted with nursing individuals. Despite the fact that many articles have examined the effects of social media usage on mental health, there is a lack of research synthesizing learning from this body of research. The purpose of this study is to use text mining and citation-based bibliometric analysis to conduct a detailed review of extant literature on health workers’ mental health and social networking habits.

This study conducts a full-text analysis of 36 articles selected on health workers' mental health and social media using text-mining techniques in R programming and a bibliometric citation analysis of 183 papers from the Scopus database in VOS viewer software. But the limitations of the methods used in this study are that the bibliometric analysis was limited to the Scopus database because the VOS viewer program did not support any other database and the text-mining approach caused the natural processing redundancy.

The bibliometric analysis reveals the thematic networks that exist in the literature of health workers’ mental health and social networking. The findings from text mining identified ten topic models, which helped to find the related papers classified in ten different groups and are provided alongside a summary of the published research and a list of the primary authors with posterior probability through Latent Dirichlet Allocation.

To the best of the authors’ knowledge, this is the first hybrid review, combining text mining and bibliometric review, on health workers’ mental health where social networking plays a moderating role. This paper critically provides an overview of the impact of social networking on health workers' mental health, presents the most important and frequent topics, introduces the scientific visualization of articles published in the Scopus database and suggests further research avenues. These findings are important for academics, health practitioners and medical specialists interested in learning how to better support the mental health of health workers using social media.