Emotional Tone Research Articles

Lexical, sentiment and correlation analysis of sacred writings. A tale of cultural influxes and different ways to interpret reality

Natural Language Processing (NLP) has transformative potential for decoding sacred writings, bridging linguistic and temporal relationships between cultures. These texts, laden with cultural and religious significance. The study analyzes texts from 14 belief systems using lexical, sentiment and correlation assessment. The analysis revealed that sacred texts are complex due to archaic language, but tend to show similar themes, historical contexts, and emotional tones. The study highlights common terms found throughout the texts, but also revealing specific terms that are influenced by the cultural context of the belief system. It also explores the various depictions of fauna and flora, uncovering the impact of spatio-temporal contexts on the composition of sacred writings. Sentiment analysis reveals polarity variations between cultures and suggest conflicts of style during translation of the texts. Comparative analysis uncovers text clusters with high similarity and cultural influences between religions that coexisted. This work showcases NLP’s potential to enhance comprehension of sacred texts and promote cross-cultural understanding.

An Automated Daily News Reports Generating Application Involving Keyword-Based News Scraping, Summarization, and Sentimental Analysis Leveraging NLP Models

In the era of information overload, obtaining relevant, concise, and sentiment-analyzed news content is essential for effective decision-making. This paper introduces an automated daily news reporting system that streamlines the process of collecting, summarizing, and analyzing the sentiment of news articles fetched based on the user's keyword. By leveraging stateof-the-art Natural Language Processing (NLP) models like GPT-3.5 for two-level summarization and BERTweet for sentiment analysis, the system provides users with concise, sentiment-labeled reports, enhancing their understanding of news trends and emotional tone. The architecture integrates data scraping, text extraction, and sentiment classification within a cloud-based Python microservice, supported by Flask. The system incorporates user localization options, allowing users to customize news retrieval by region and time preferences. Finalized reports are formatted into HTML and delivered directly to authenticated user emails through Gmail API, ensuring seamless and secure distribution. This research underscores the significance of automated news summarization and sentiment analysis in modern information retrieval. It provides a scalable and personalized solution that enables real-time synthesis of large volumes of news content, making it accessible and relevant for diverse audiences worldwide.

Emotions and entrepreneurial finance: Analysis of venture capitalists’ and business angels’ digital footprints on Twitter

Emotions are a central concept in previous entrepreneurship research, but this is mainly related to entrepreneurs and their entrepreneurial journey. However, venture capitalists (VCs) and business angels (BAs), two critical investors in the entrepreneurial finance literature, are essential actors in the entrepreneurial process. Still, little is known about investor emotions in this context. Therefore, in this study, we ask how venture capitalists differ from business angels in terms of their expressed emotions. To this end, we use an increasingly familiar research approach by examining the digital footprints of these investors on Twitter. For this purpose, we identify 822 investors from Crunchbase and analyze their 994,969 Tweets with Linguistic Inquiry and Word Count (LIWC) as a text analysis tool. Our results show that venture capitalists display more positive emotions on Twitter than angel investors, meaning that we find an association between VCs and emotional tone. Furthermore, in our post-hoc analysis, we explore further explanations for the differences between VC and BA. In doing so, we show differences in their expressed cognitive processes as well as in their communicated drivers. In both concepts, we find positive associations with the investor type of VC. To conclude this paper, we develop implications for practice and further research based on the results.

Impact of algorithm-driven comments on corrective information among young adults: focusing on emotional tone of comments and misinformation credibility

PurposeWhen facilitating transmission of health information from government officials to the public, social media employs algorithms that selectively expose users to specific perspectives, even for accurate health-related information from official sources. The purpose of this study was to explore impact of algorithm-driven comments characterized by different emotional tones (i.e. positive vs. negative vs. mixed) on users’ perceptions of credibility of corrective information to examine misinformation about flu vaccines aimed at young adults. Additionally, this study explored how prior misinformation credibility acted as an intervening variable in shaping the impact of algorithmically generated comments with diverse emotional tones on credibility of corrective information, with algorithm credibility serving as a mediator.Design/methodology/approachAn online experiment was conducted with 275 participants recruited from Amazon Mechanical Turk (MTurk). Young adults from the USA aged between 18 and 35 years who were also users of Instagram were eligible for participating in this study as this study utilized Instagram platform for stimuli.FindingsResults highlighted a diminished impact of algorithm-generated negative comments on perceived credibility of corrective information. Additionally, individuals with high misinformation credibility demonstrated a stronger tendency to trust algorithms featuring negative comments, underscoring the significant impact of algorithm-driven negativity in shaping trust dynamics for this group. Notably, credibility of the algorithm among individuals with high misinformation credibility did not translate into increased credibility for corrective information. This suggests that strategically designing algorithms to emphasize supportive or diverse opinions can be an effective approach to alleviate potential negative consequences associated with accurate information.Originality/valueThis research signifies the initial effort to disentangle the dynamics between negativity bias and cue routes within the algorithmic framework, shaping individuals’ perceptions of credibility of accurate health-related information contingent on accompanying comments. In the context of social media platforms that embrace diverse opinions, it emphasizes the critical necessity for tailored algorithmic strategies to effectively deliver accurate information.

Weather, climate, and atmospheres. An application to the landscape

The aim of this article is to examine how weather phenomena affect the landscape, not only in terms of its visual or geomorphological appearance, but also by modifying the emotional disposition that the landscape evokes. By adopting an atmospheric perspective, I intend to demonstrate that each landscape possesses its own mood (Stimmung), closely linked to the atmospheric-climatic events that unfold within it. My hypothesis is that such phenomena, due to their pervasiveness on a sensory level, can produce a real metamorphosis of the landscape, which also extends to the affective qualities that the landscape ‘radiates’, and which therefore do not primarily depend on the perceiver. My analysis is structured into two parts. In the first part, a) I attempt to prove that meteorological and climatic atmospheres, due to their extra-psychic nature, cannot be explained in empathic-projective terms; and b) I propose understanding the landscape as an expressive whole whose ‘emotional physiognomy’ changes according to the atmospheres that pass through it. In the second part, I support my argument with a literary example to show how the fundamental emotional tone (Grundstimmung) of the landscape can change radically following the manifestation of a specific atmospheric phenomenon.

Exploring the Perspectives of Older Adults on a Digital Brain Health Platform Using Natural Language Processing: Cohort Study.

Although digital technology represents a growing field aiming to revolutionize early Alzheimer disease risk prediction and monitoring, the perspectives of older adults on an integrated digital brain health platform have not been investigated. This study aims to understand the perspectives of older adults on a digital brain health platform by conducting semistructured interviews and analyzing their transcriptions by natural language processing. The study included 28 participants from the Boston University Alzheimer's Disease Research Center, all of whom engaged with a digital brain health platform over an initial assessment period of 14 days. Semistructured interviews were conducted to collect data on participants' experiences with the digital brain health platform. The transcripts generated from these interviews were analyzed using natural language processing techniques. The frequency of positive and negative terms was evaluated through word count analysis. A sentiment analysis was used to measure the emotional tone and subjective perceptions of the participants toward the digital platform. Word count analysis revealed a generally positive sentiment toward the digital platform, with "like," "well," and "good" being the most frequently mentioned positive terms. However, terms such as "problem" and "hard" indicated certain challenges faced by participants. Sentiment analysis showed a slightly positive attitude with a median polarity score of 0.13 (IQR 0.08-0.15), ranging from -1 (completely negative) to 1 (completely positive), and a median subjectivity score of 0.51 (IQR 0.47-0.53), ranging from 0 (completely objective) to 1 (completely subjective). These results suggested an overall positive attitude among the study cohort. The study highlights the importance of understanding older adults' attitudes toward digital health platforms amid the comprehensive evolution of the digitalization era. Future research should focus on refining digital solutions to meet the specific needs of older adults, fostering a more personalized approach to brain health.

Collaborative AI in the workplace: Enhancing organizational performance through resource-based and task-technology fit perspectives

This research examines how artificial intelligence, human capabilities, and task types influence organizational outcomes. By leveraging the frameworks of the Resource-Based View and Task Technology Fit theories, we executed two distinct studies to assess the effectiveness of a generative AI tool in aiding task performance across a spectrum of task complexities and creative demands. The initial study tested the utility of generative AI across diverse tasks and the significance of AI-related skills enhancement. The subsequent study explored interactions between humans and AI, analyzing emotional tone, sentence structure, and word choice. Our results indicate that incorporating AI can significantly improve organizational task performance in areas such as automation, support, creative endeavors, and innovation processes. We also observed that generative AI generally presents more positive sentiment, utilizes simpler language, and has a narrower vocabulary than human counterparts. These insights contribute to a broader understanding of AI's strengths and weaknesses in organizational settings and guide the strategic implementation of AI systems.

Exploring the Impact of Word2Vec Embeddings Across Neural Network Architectures for Sentiment Analysis

Abstract. Sentiment analysis is crucial for understanding public opinion, gauging customer satisfaction, and making informed business decisions based on the emotional tone of textual data. This study investigates the performance of different Word2Vec-based embedding strategies static, non-static, and multichannel for sentiment analysis across various neural network architectures, including Convolution Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRUs). Despite the rise of advanced contextual embedding methods such as Bidirectional Encoder Representations from Transformers (BERT), Word to Vector (Word2Vec) retains its importance due to its simplicity and lower computational demands, making it ideal for use in settings with limited resources. The goal is to evaluate the impact of fine-tuning Word2Vec embeddings on the accuracy of sentiment classification. Using the Internet Movie Database (IMDb), this work finds that multichannel embeddings, which combine static and non-static representations, provide the best performance across most architectures, while static embeddings continue to deliver strong results in specific sequential models. These findings highlight the balance between efficiency and accuracy in traditional word embeddings, particularly when advanced models are not feasible.

Emerging Adults With a Suicide Attempt History Text More Emotionally With Peers than Family Members

Emotional communication is central to strong interpersonal relationships and mental health. For emerging adults, much of their interpersonal communication happens via texting, but we know little about how and with whom their emotional texting occurs. Understanding these patterns may be especially critical for emerging adults experiencing mental health crises (e.g., suicidality). This study examined how the emotional tone of texts (sent and received) varies based on texting partner (i.e., peers, which includes friends and significant others, vs. family) and within-person suicide risk. Participants were 27 emerging adults with prior, non-lethal suicide attempt(s). Linguistic Inquiry Word Count was used to label 75,928 texts. While there was variation in the specific interactions, results overall indicated that participants exchanged texts containing all emotion category words at greater rates with peers (vs. family), and this pattern generally held across within-person suicide risk level. Implications for suicide prevention/intervention efforts are discussed.

Exploring the Impact of Word2Vec Embeddings Across Neural Network Architectures for Sentiment Analysis

Abstract. Sentiment analysis is crucial for understanding public opinion, gauging customer satisfaction, and making informed business decisions based on the emotional tone of textual data. This study investigates the performance of different Word2Vec-based embedding strategies static, non-static, and multichannel for sentiment analysis across various neural network architectures, including Convolution Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRUs). Despite the rise of advanced contextual embedding methods such as Bidirectional Encoder Representations from Transformers (BERT), Word to Vector (Word2Vec) retains its importance due to its simplicity and lower computational demands, making it ideal for use in settings with limited resources. The goal is to evaluate the impact of fine-tuning Word2Vec embeddings on the accuracy of sentiment classification. Using the Internet Movie Database (IMDb), this work finds that multichannel embeddings, which combine static and non-static representations, provide the best performance across most architectures, while static embeddings continue to deliver strong results in specific sequential models. These findings highlight the balance between efficiency and accuracy in traditional word embeddings, particularly when advanced models are not feasible.

Public attitudes toward higher education using sentiment analysis and topic modeling

This study examines higher education through data-mining methodologies, aiming to uncover key themes and sentiments in global discourse. Utilizing sentiment analysis and topic modeling, the research analyzes 157,943 tweets from 84,423 unique users over a five-month period (January to May 2023). This period was selected, coinciding with the rise of artificial intelligence (AI) tools, particularly ChatGPT. The study investigates the discussions, emotional tones, and dominant topics shaping the global narrative of higher education within X (Twitter) data. Key findings include the geographical distribution of tweets and the most frequent positive and negative perceptions. It also addresses critical issues such as affordability, accessibility, and funding in higher education. Furthermore, the data shows public reactions to AI in higher education are initially negative, while higher education tweets are primarily characterized by positivity and optimism. The higher education tweets are mainly posted on the weekend, with decreased activity during weekdays. This research provides insights into the evolving higher education landscape amid rapid technological advancements.

Empowering Thai community pharmacists in combating antimicrobial resistance: Qualitative insight and sentiment analysis

BackgroundAntimicrobial resistance (AMR) is increasing globally and poses a significant public health challenge. Community pharmacists, especially in primary care settings, play a pivotal role in mitigating the irrational use of antibiotics, a key driver of AMR. ObjectivesThis study aims to explore qualitative insights from community pharmacists regarding antibiotic supply and usage, analyze sentiments related to AMR, and highlight the crucial role of community pharmacists in AMR stewardship at the primary care/community level. MethodsThis study engaged community pharmacists in Thailand through semi-structured interviews to obtain in-depth insights into the antibiotic supply and perceptions of AMR. Additionally, sentiment analysis, which evaluates the emotional tone of the pharmacists' responses, was conducted to enrich the findings. ResultsInterviews with 23 community pharmacists highlighted the practices, challenges, and strategies related to antibiotic supply and use. Key findings include the identification of barriers such as patient demand and lack of awareness about antimicrobial resistance (AMR), alongside strategies for improvement such as public education and professional development. Sentiment analysis reveals a cautiously optimistic perspective toward enhancing rational antibiotic use, underscoring the importance of comprehensive approaches that combine education, ethics, and regulatory measures to address the complexities of antibiotic management at community pharmacies. ConclusionThis study underscores the necessity of public awareness, pharmacist–patient relationships, and regulatory reforms for the rational use of antibiotics in community pharmacies. These findings emphasize that pharmacist education and adherence to professional ethics are essential for mitigating antimicrobial resistance and promoting rational antibiotic use.

Artificial intelligence chatbots versus traditional medical resources for patient education on “Labor Epidurals”: An evaluation of accuracy, emotional tone, and readability

Artificial intelligence chatbots versus traditional medical resources for patient education on “Labor Epidurals”: An evaluation of accuracy, emotional tone, and readability

Gay Dreams: Exploring the Relationship Between Sexual Orientation and Dream Content in Men.

Although numerous individual factors influencing dream content have been explored, research on the link between sexual orientation and dreaming remains limited. This study examined this relationship among 119 German-speaking men (mean age = 31.97 years), including 55homosexual and 64heterosexual participants. Participants completed a questionnaire on their waking life sexuality and dreams and provided two dream reports. Homosexual men reported more sexual partners in waking life and lower satisfaction with their sexual orientation compared to heterosexual men. No significant differences were found in dream recall frequency, emotional tone, nightmare frequency, or distress, though homosexual men reported more sexual dreams. Dream reports showed no significant differences in sexual interactions or the number of sexual partners between groups, but homosexual men's dreams featured a higher ratio of male to female characters and more romantic relationships with men. These findings partially align with the continuity hypothesis, suggesting that the dream content of homosexual men reflects their social interactions and romantic preferences. Overall, the study suggests that homosexual and heterosexual men share a similar dream pattern. The implications of these findings highlight the importance of considering sexual orientation in dream research to better understand the intersection of sexuality and unconscious processes.

“I Changed After the Death”: Symptoms of Psychopathology Predict Lower Agency and Communion Themes in Loss Narratives Over 16 Months

Abstract Purpose Some individuals struggle to adjust after the death of a close other. Constructing an adaptive narrative about the loss is important to adjustment but symptoms of psychopathology may interfere with this process. We examined whether psychopathology symptoms measured 2 months after the loss of a spouse or parent predicted loss narratives with lower agency and communion themes as well as more negative emotional tone and self-event connections. Method Participants included 507 adults from the Aarhus Bereavement Study who completed psychopathology symptom measures at 2, 6, 11, and 18 months after the death of their spouse or parent. Symptom measures included prolonged grief disorder (PGD), PTSD, depression, and anxiety. Eighteen months after the death, participants wrote a narrative about the loss and answered questions about its emotional qualities (i.e., tone, self-event connections). The narratives were content coded for agency and communion themes. Results Multiple regressions showed that higher PGD symptoms at 2 months predicted less adaptive loss narratives at 18 months, even after controlling for neuroticism and age. Conclusion Individuals who experience high symptom levels are struggling to construct adaptive loss narratives. This may hinder identity changes needed to accommodate their altered life circumstances.

Topic modelling and sentiment analysis during COVID-19 revealed emotions changes for public health

Between 2020 and 2022, lockdown and restraining measures as a result of the COVID-19 pandemic led to changes in daily routines and also in language usage. At certain points during the pandemic, populations in some countries were unwilling or unlikely to respond to government messages, either because of the tone and analytic discourse used by leaders, or because they did not understand the messages. Linguistic markers and meanings were therefore linked to low levels of engagement, negative emotions and high levels of analytical thinking, especially in relation to the discourses of influential international leaders. We subjected sixteen speeches by eight country leaders to topic modelling and sentiment analysis in order to understand how the psychological functions of language were affected during two different periods of the COVID-19 pandemic. In this topic analysis we organize 39,073 words collected from sixteen authentic speeches delivered in two different periods of the acute phase of the pandemic. These were encoded in the Linguistic Inquiry Word Count program (LIWC), with the main aim being to identify differences between the periods. We examined the following aspects: (1) the emotional tone, analytical thinking and clout (empathy dimension); (2) the changes in these three dimensions or factors between periods 1 and 2 (February and May 2020). We observed a negative relationship between emotional tone and analytical thinking and a positive relationship between clout and emotional tone. When we considered the changes in pandemic circumstances, the psycholinguistic profiles of eight country leaders demonstrated fluctuations in language and emotions. Further reviews and research should focus on the current language and deficit wording of this population (leaders). We also note that psychologists and schoolteachers can play an important role in supporting language programmes with positive wording and by emphasising the collateral effects of face-to-face classes when teaching children to read and write.

Enhancing Metaphor Recognition of Literary Works in Applied Artificial Intelligence: A Multi-Level Approach with Bi-LSTM and CNN Fusion

ABSTRACT Understanding metaphorical language is essential for AI to interpret and communicate with humans accurately. However, current methods often struggle with the complexity of metaphors, making it difficult for AI systems to understand human language fully. Recognizing metaphors is challenging because they are frequently ambiguous and depend on context. In this study, we propose a new approach using a combination of Bi-directional Long Short-Term Memory (Bi-LSTM) networks, Convolutional Neural Networks (CNN), and uni-directional LSTM components to create a multi-level model for recognizing metaphors. Our model uses various features, including dependency, semantics, and part-of-speech, to improve its learning ability. Additionally, we introduce a new method for recognizing the emotional context of metaphors using a random walk model to determine the emotional tone of words. Our results show that this model improves performance in recognizing metaphors, enhancing AI’s ability to understand them.

Letters of Historians of the 2nd Half of the 20th Century as a Channel of Scholarly and Business Communications (Based on Letters from Siberia to the Capital)

The article analyzes the letters of specialists in Russian history of the 17th – 19th centuries who sent correspondences to their colleagues in Moscow. The reason these letters are being analyzed is because, due to the distance and communication methods available at the time, correspondence was the main way for Siberian scholars to communicate with the representatives of the important scientific centers, to stay updated on the latest research trends and discoveries. During this era, authors were comparatively unrestricted in their statements, and their internal and external interactions were diverse and significant. Historians from Siberia and Moscow used to correspond on scientific and organizational matters through letters. The topics of discussions included participation in scientific conferences, invitations, opportunities for business trips, publications, cooperation, and reviews. The scholars shared their professional thoughts, ideas, and plans, characterized the sources they found and analyzed, expressed hypotheses and explained preliminary conclusions, reported the outcomes of research, and sometimes talked about the progress in their research projects and the development in their understanding of scientific problems. The letters often described events in the scientific careers of the authors. The content and emotional tone of the correspondence were significantly influenced by the author's character and relationship with the addressee. The letters often contained information of both scientific and personal nature. Sometimes, Siberian scientists requested assistance and help from their colleagues from the capital. The article concludes that letters were a reliable and effective communication channel among the professional community of historians. They were used to convey scientific, business, and occasionally personal information. The recipients of these letters were typically scholars from Moscow who were older in age and higher in status. As a reference group, they played a significant role in determining the specifics of the letters addressed to them.

Emotional Tone and Authenticity of World Governments’ Discourse Concerning Monkeypox: A Psycholinguistics Analysis

The discourses of Monkeypox relating to linguistics segments may contain a person's emotional tone and authenticity discourse from psychology. This article presents a psycholinguistic analysis of the discourse used by world governments during the monkeypox outbreak. It examines the emotional tone and authenticity of the language used by government officials in their discourses to the public. Therefore, this study used psycholinguistics analysis which adopt the Linguistics Inquiry Word Counts (LIWC) program to compute the text into a word count numbers with the average number of emotional tone and authenticity. The findings showed that emotional tone and authenticity of the discourse can have a significant impact on how the audience receives and interprets the message. Accordingly, the use of authentic communication strategies can enhance public trust and confidence in the government's ability to manage a crisis. It brings the implication that government officials should use language features that reflect a high level of authenticity, such as first-person pronouns and negative adjectives, to establish trust and confidence in their leadership during a public health crisis.

Technological Advancements in Menstrual Health: The Role of Generative Pre-Trained Transformer and Bees Algorithm

This paper introduces the concept of a smart menstrual cup, incorporating advanced technology to address challenges associated with traditional menstrual health management methods. The proposed method, Hybrid Bidirectional Encoder Generative Transformer based Bees Search (Hybrid BEGT-BS), aims to enhance the longevity and reliability of smart menstrual cups. The Generative Pre-trained Transformer (GPT) is employed to extract key information and determine emotional tones related to menstruation, while the Bidirectional Encoder Representations from Transformer (BERT) classifies menstrual-related data such as cycle tracking, hygiene, and symptoms. Further different validation metrics such as F1-score, specificity, Area Under the Curve-Receiver Operating Characteristic (AUC-ROC), Mean Squared Error (MSE), recall, energy consumption, accuracy, and precision are employed to assess the method's effectiveness. From the comparative results it demonstrates the superior performance of the Hybrid BEGT-BS method in enhancing the performance of smart menstrual cups.