Search results

Technology acceptance is a measure of that technology’s usefulness. Oil palm is one of the biggest contributors to Indonesia’s revenues, thus fueling its economy. Using remote sensing would allow a plantation to monitor and forecast its production and the amount of fertilizer used. This review aims to provide a policy recommendation in the form of a strategy to improve the added value of Indonesia’s oil palm and support the government in increasing oil palm production. This recommendation needs to be formulated by determining the users’ acceptance of remote sensing technology (state-owned plantations, private plantation companies and smallholder plantations).

This review’s methodology used sentiment analysis through text mining (bag of words model). The study’s primary data were from focus group discussions (FGDs), questionnaires, observations on participants, audio-visual documentation and focused discussions based on group category. The results of interviews and FGDs were transcribed into text and analyzed to 1) find words that can represent the content of the document; 2) classify and determine the frequency (word cloud); and finally 3) analyze the sentiment.

The result showed that private plantation companies and state-owned plantations had extremely high positive sentiments toward using remote sensing in their oil palm plantations, whereas smallholders had a 60% resistance. However, there is still a possibility for this technology’s adoption by smallholders, provided it is free and easily applied.

Basically, technology is applied to make work easier. However, not everyone is tech-savvy, especially the older generations. One dimension of technology acceptance is user/customer retention. New technology would not be immediately accepted, but there would be user perceptions about its uses and ease. At first, people might be reluctant to accept a new technology due to the perception that it is useless and difficult. Technology acceptance is the gauge of how useful technology is in making work easier compared to conventional ways.

Therefore, technology acceptance needs to be improved among smallholders by intensively socializing the policies, and through dissemination and dedication by academics and the government.

The social implications of using technology are reducing the workforce, but the company will be more profitable and efficient.

Remote sensing is one of the topics that people have not taken up in a large way, especially sentiment analysis. Acceptance of technology that utilizes remote sensing for plantations is very useful and efficient. In the end, company profits can be allocated more toward empowering the community and the environment.

The goal of this work is to evaluate how digital transformation disclosure in corporate news and press releases affects stock prices. We examine American and Chinese companies from the energy and industry sectors for two periods: pre-COVID-19 and during the COVID-19 pandemic.

To estimate the effects of disclosure of information related to digital transformation, we applied the bag-of-words (BOW) method. As the benchmark dictionary, we used Kindermann et al. (2021), with the addition of original dictionaries created via Latent Dirichlet allocation (LDA) analysis. We also employed panel regression analysis and random forest.

For USA energy sector, all aspects of digital transformation were insignificant in pre-COVID-19 period, while sustainability topics became significant during the pandemic. As for the Chinese energy sector, digital strategy implementation was significant in pre-pandemic period, while digital technologies adoption and business model innovation became relevant in COVID-19 period. The results show the greater significance of digital transformation aspects for industrials sectors compared to the energy sector. The result of random forest analysis proves the efficiency of the authors’ dictionary which could be applied in practice. The developed methodology can be considered relevant.

The research contributes to the existing literature in theoretical, empirical and methodological ways. It applies signaling and information asymmetry theories to the financial markets, digital transformation being used as an instrument. The methodological contribution of this article can be described in several ways. Firstly, our data collection process differs from that in previous papers, as the data are gathered “from investor’s point of view”, i.e. we use all public information published by the company. Secondly, in addition to the use of existing dictionaries based on Kindermann et al. (2021), with our own modifications, we apply the original methodology based on LDA analysis. The empirical contribution of this research is the following. Unlike past works, we do not focus on particular technologies (Hong et al., 2023) connected with digital transformation, but try to cover all multi-dimensional aspects of the transformational process and aim to discover the most significant one.

The metaverse, which is now revolutionizing how brands strategize their business needs, necessitates understanding individual opinions. Sentiment analysis deciphers emotions and uncovers a deeper understanding of user opinions and trends within this digital realm. Further, sentiments signify the underlying factor that triggers one’s intent to use technology like the metaverse. Positive sentiments often correlate with positive user experiences, while negative sentiments may signify issues or frustrations. Brands may consider these sentiments and implement them on their metaverse platforms for a seamless user experience.

The current study adopts machine learning sentiment analysis techniques using Support Vector Machine, Doc2Vec, RNN, and CNN to explore the sentiment of individuals toward metaverse in a user-generated context. The topics were discovered using the topic modeling method, and sentiment analysis was performed subsequently.

The results revealed that the users had a positive notion about the experience and orientation of the metaverse while having a negative attitude towards the economy, data, and cyber security. The accuracy of each model has been analyzed, and it has been concluded that CNN provides better accuracy on an average of 89% compared to the other models.

Analyzing sentiment can reveal how the general public perceives the metaverse. Positive sentiment may suggest enthusiasm and readiness for adoption, while negative sentiment might indicate skepticism or concerns. Given the positive user notions about the metaverse’s experience and orientation, developers should continue to focus on creating innovative and immersive virtual environments. At the same time, users' concerns about data, cybersecurity and the economy are critical. The negative attitude toward the metaverse’s economy suggests a need for innovation in economic models within the metaverse. Also, developers and platform operators should prioritize robust data security measures. Implementing strong encryption and two-factor authentication and educating users about cybersecurity best practices can address these concerns and enhance user trust.

In terms of societal dynamics, the metaverse could revolutionize communication and relationships by altering traditional notions of proximity and the presence of its users. Further, virtual economies might emerge, with virtual assets having real-world value, presenting both opportunities and challenges for industries and regulators.

The current study contributes to research as it is the first of its kind to explore the sentiments of individuals toward the metaverse using deep learning techniques and evaluate the accuracy of these models.

This paper purposed a multi-facet sentiment analysis system.

Hence, This paper uses multidomain resources to build a sentiment analysis system. The manual lexicon based features that are extracted from the resources are fed into a machine learning classifier to compare their performance afterward. The manual lexicon is replaced with a custom BOW to deal with its time consuming construction. To help the system run faster and make the model interpretable, this will be performed by employing different existing and custom approaches such as term occurrence, information gain, principal component analysis, semantic clustering, and POS tagging filters.

The proposed system featured by lexicon extraction automation and characteristics size optimization proved its efficiency when applied to multidomain and benchmark datasets by reaching 93.59% accuracy which makes it competitive to the state-of-the-art systems.

The construction of a custom BOW. Optimizing features based on existing and custom feature selection and clustering approaches.

In this study, the author examines the effect of managers’ perception of product market competition on accruals and real earnings management.

The author develops a new text-based measure of the emphasis managers place on product market competition by conducting a textual analysis of firms’ 10-K filings. Using this measure, the author conducts a battery of econometric analyses and robustness checks to investigate the impact of this measure of product market competition on measures of accruals and real earnings management.

This study finds robust evidence that when management perceives more competitive threats, they are more likely to engage in accruals-based earnings manipulation but are less likely to engage in real earnings management activity. The author argues that these findings are due to managers’ career concerns enticing them to manage earnings via accrual when competition is high, but that greater product market competition discourages real earning management activity as it can diminish firms’ competitiveness.

The findings of this paper have important policy and practical implications since it signals that managers’ perceptions of product market competition is able to affect accounting choices, information environments and economic outcomes in firms.

This study develops a new text-based measure of managers’ perception of product market competition with the aid of GPT-4. The author then using this measure provides firm-level evidence on how this relates to earnings management.

The purpose of the study is to identify the latent topics from 9102 Web of Science (WoS) indexed research articles published in 2645 journals of the Sri Lankan authors from 1989 to 2021 by applying Latent Dirichlet Allocation to the abstracts. Dominant topics in the corpus of text, the posterior probability of different terms in the topics and the publication proportions of the topics were discussed in the article.

Abstracts and other details of the studied articles are collected from WoS database by the authors. Data preprocessing is performed before the analysis. “ldatuning” from the R package is applied after preprocessing of text for deciding subjects in light of factual elements. Twenty topics are decided to extract as latent topics through four metrics methods.

It is observed that medical science, agriculture, research and development and chemistry-related topics dominate the subject categories as a whole. “Irrigation” and “mortality and health care” have a significant growth in the publication proportion from 2019 to 2021. For the most occurring latent topics, it is seen that terms like “activity” and “acid” carry higher posterior probability.

Topic models permit us to rapidly and efficiently address higher perspective inquiries without human mediation and are also helpful in information retrieval and document clustering. The unique feature of this study has highlighted how the growth of the universe of knowledge for a specific country can be studied using the LDA topic model.

This study will create an incentive for text analysis and information retrieval areas of research. The results of this paper gave an understanding of the writing development of the Sri Lankan authors in different subject spaces and over the period. Trends and intensity of publications from the Sri Lankan authors on different latent topics help to trace the interests and mostly practiced areas in different domains.

Improving the diversity of recommendation information has become one of the latest research hotspots to solve information cocoons. Aiming to achieve both high accuracy and diversity of recommender system, a hybrid method has been proposed in this paper. This study aims to discuss the aforementioned method.

This paper integrates latent Dirichlet allocation (LDA) model and locality-sensitive hashing (LSH) algorithm to design topic recommendation system. To measure the effectiveness of the method, this paper builds three-level categories of journal paper abstracts on the Web of Science platform as experimental data.

(1) The results illustrate that the diversity of recommended items has been significantly enhanced by leveraging hashing function to overcome information cocoons. (2) Integrating topic model and hashing algorithm, the diversity of recommender systems could be achieved without losing the accuracy of recommender systems in a certain degree of refined topic levels.

The hybrid recommendation algorithm developed in this paper can overcome the dilemma of high accuracy and low diversity. The method could ameliorate the recommendation in business and service industries to address the problems of information overload and information cocoons.

The purpose of this paper is to explore the reaction of Pakistani citizens toward online privacy in the context of the Pakistan Government's COVID-19 app privacy breach.

The authors implemented supervised and unsupervised machine learning methods, that is, topic modeling and sentiment analysis on Google app store user review data.

There was no visible concern shown by the citizens toward the COVID-19 app privacy breach, even though it was well highlighted in the news. Other studies have also indicated that concern for online privacy remains low in developing countries, which aligns with the findings of this paper.

Globally COVID-19 apps have been a cause of concern in terms of public privacy. To the best of the authors’ knowledge, this paper is the first in the Pakistani context to show the impact of a well-document privacy breach of a government COVID-19 app.

The study examines the relationship between news intensity, media sentiment and market microstructure invariance-implied measures of trading activity and liquidity of Chinese property developer stocks during the 2020–2022 Chinese property sector crisis.

The authors adopt the extension of the news article invariance hypothesis, which is a generalization of the market microstructure invariance conjecture, from January 2020 to January 2022 to test specific quantitative relationships between the arrival rate of public information, trading activity and a nonlinear function of a proxy for the probability of informed trading. Empirical tests are based on a dataset of 22,412 firm-day observations and two count-data models to correct for overdispersion and the excess number of zeros. Seventy-five stocks of Chinese companies from the property development industry (including the China Evergrande Group) were included in the sample.

The authors reject the news article invariance hypothesis but document a positive and significant relationship between the flow of public information and risk liquidity. Additionally, the authors find that the proxy for informed trading activity is positively related to the arrival rates of public information from October 2021 to January 2022.

The findings support the hypothesis that negative (positive) media sentiment induces significant deterioration (insignificant improvement) in stock liquidity. The authors find that an increase in the number of news articles about a company corresponds to a higher liquidity of Chinese property developers' stocks after controlling for media sentiment.

This paper aims to focus on extracting aspect terms on mobile phone (iPhone and Samsung) tweets using NLTK techniques on multiple aspect extraction is one of the challenges. Then, also machine learning techniques are used that can be trained on supervised strategies to predict and classify sentiment present in mobile phone tweets. This paper also presents the proposed architecture for the extraction of aspect terms and sentiment polarity from customer tweets.

In the aspect-based sentiment analysis aspect, term extraction is one of the key challenges where different aspects are extracted from online user-generated content. This study focuses on customer tweets/reviews on different mobile products which is an important form of opinionated content by looking at different aspects. Different deep learning techniques are used to extract all aspects from customer tweets which are extracted using Twitter API.

The comparison of the results with traditional machine learning methods such as random forest algorithm, K-nearest neighbour and support vector machine using two data sets iPhone tweets and Samsung tweets have been presented for better accuracy.

In this paper, the authors have focused on extracting aspect terms on mobile phone (iPhone and Samsung) tweets using NLTK techniques on multi-aspect extraction is one of the challenges. Then, also machine learning techniques are used that can be trained on supervised strategies to predict and classify sentiment present in mobile phone tweets. This paper also presents the proposed architecture for the extraction of aspect terms and sentiment polarity from customer tweets.