Sentiment Analysis of Users’ Comments on Indian Hindi News Channels Using Mozdeh: An Evaluation Based on YouTube Videos

Sentiment analysis is the channel to pick out the text from the social media dataset to inquire about the positive and negative opinions of the statement and its subjective and objectiveness. The purpose of the study is to manifest the sentiment of the text posted in five Hindi news channels, that is, AajTak, ABP News, India TV, NDTV India and Republic Bharat on YouTube are investigated by adopting the Mozdeh software to highlight the sequential temperament of the viewers by evaluating the positive and negative sentiments. The present study is subsequently limited to the data being extracted and evaluated by the software Mozdeh. The sentiments of each Hindi news channel are analysed along with the top word frequencies and displaying the time-series graph. The investigation presents that the channel with maximum average positive average negative sentiment belongs to India TV and the female category was in the peak compared to male altogether but the unidentified gender was the highest. During the time series analysis, the year 2020 was seen to be the most productive year since all the spikes were precisely detected. The audience of these channels turns out to be more attentive towards the political and entertainment news world. The study also highlights the tendency and interest of the common audiences to watch the news which dedicates that people are usually unsatisfied with the content being displayed in the videos and the common concentration is mostly based on the political news.

Leveraging Text Mining Approach to Identify What People Want to Know About Mental Disorders From Online Inquiry Platforms

Online inquiry platforms, which is where a person can anonymously ask questions, have become an important information source for those who are concerned about social stigma and discrimination that follow mental disorders. Therefore, examining what people inquire about regarding mental disorders would be useful when designing educational programs for communities. The present study aimed to examine the contents of the queries regarding mental disorders that were posted on online inquiry platforms. A total of 4,714 relevant queries from the two major online inquiry platforms were collected. We computed word frequencies, centralities, and latent Dirichlet allocation (LDA) topic modeling. The words like symptom, hospital and treatment ranked as the most frequently used words, and the word my appeared to have the highest centrality. LDA identified four latent topics: (1) the understanding of general symptoms, (2) a disability grading system and welfare entitlement, (3) stressful life events, and (4) social adaptation with mental disorders. People are interested in practical information concerning mental disorders, such as social benefits, social adaptation, more general information about the symptoms and the treatments. Our findings suggest that instructions encompassing different scopes of information are needed when developing educational programs.

YorAA: An Authorship Attribution of Yorùbá Texts

The process of establishing the most likely author of a collection of texts or documents whose authorship must be verified is known as authorship attribution. Several studies have been reported in the literature on the task, but rarely any reported work on Yorùbá language texts. In this paper, the development of an automatic Yorùbá written texts authorship attribution system (YorAA) is reported. The literary works of six Yorùbá authors were considered. Stylometry features were extracted from the texts using the BoW approach and lexical/syntactic word frequencies approach. The Support Vector Machine, Multilayer Perceptron and Random Forest algorithms were used for the classification analysis. The experimental results showed that the developed YorAA system achieved accuracy, recall, precision and F1 measures values of 95%, 83%, 84% and 84% respectively on the average, for all the six authors. The results demonstrate that with a database of written texts in Yorùbá language, that is enough to extract relevant stylometry ´ features of the author and appropriate methods and tools applied to such features; the authorship of the texts can be identified or verified.

Cross-Topic Author Identification -- a Case Study on Swedish Literature

Using material from the Swedish Literature Bank, we investigate whether common methods of author identification using word frequencies and part of speech frequencies are sensitive to differences in topic. The results show that this is the case, thereby casting doubt on much previous work in author identification. This sets the stage for a broader future study, comparing other methods and generalising the results.

Leveraging Text Mining Approach to Identify What People Want to Know About Mental Disorders from Online Inquiry Platforms (Preprint)

BACKGROUND Online inquiry platforms, which is where a person can anonymously ask questions, have become an important information source for those who are concerned about social stigma and discrimination that follow mental disorders. Therefore, examining what people inquire about regarding mental disorders would be useful when designing educational programs for communities. OBJECTIVE The present study aimed to examine the contents of the queries regarding mental disorders that were posted on online inquiry platforms. METHODS A total of 4,714 relevant queries from the two major online inquiry platforms were collected. We computed word frequencies, centralities, and latent Dirichlet allocation (LDA) topic modeling. RESULTS The words like symptom, hospital and treatment ranked as the most frequently used words, and the word my appeared to have the highest centrality. Results: Four topics exist according to the LDA, which are 1) understanding general symptoms, 2) disability grading system and welfare entitlement, 3) stressful life events, and (4) social adaptation with mental disorders. CONCLUSIONS People are interested in practical information concerning mental disorders, such as social benefits, social adaptation, and more general information about the symptoms and the treatments. Our findings suggest that instructions encompassing different scopes of information are needed when developing educational programs.

Within-sample, but not corpus-based word frequency of verbal fluency output is associated with positive symptoms in schizophrenia

Previous research on word frequency during speech production in schizophrenia is scant and inconclusive. Furthermore, there may exist methodological difficulties in utilizing corpus-based word frequencies, while adequate corpora are not available for all languages. We calculated (1) corpus-based and (2) within-sample word frequencies of output on verbal fluency in 36 patients with schizophrenia and tested their associations with positive and negative symptoms. Within-sample word frequency was calculated as the number of subjects in the sample who produced the word. Within-sample but not corpus-based word frequencies displayed normal, non-skewed, and non-kurtic data distributions. Within-sample but not corpus-based word frequencies were significantly correlated with the severity of delusions and bizarre behavior. We propose that the within-sample word frequency might be a valuable alternative to corpus-based word frequencies in clinical research.

Influencing factors and mechanism of doctor consultation volume on online medical consultation platforms based on physician review analysis

PurposeThis paper aims to reveal the factors patients consider when choosing a doctor for consultation on an online medical consultation (OMC) platform and how these factors influence doctors' consultation volumes.Design/methodology/approachIn Study 1, influencing factors reflected as service features were identified by applying a feature extraction method to physician reviews, and the importance of each feature was determined based on word frequencies and the PageRank algorithm. Sentiment analysis was used to analyze patient satisfaction with each service feature. In Study 2, regression models were used to analyze the relationships between the service features obtained from Study 1 and the doctor's consultation volume.FindingsThe study identified 14 service features of patients' concerns and found that patients mostly care about features such as trust, phraseology, overall service experience, word of mouth and personality traits, all of which describe a doctor's soft skills. These service features affect patients' trust in doctors, which, in turn, affects doctors' consultation volumes.Originality/valueThis research is important as it informs doctors about the features they should improve, to increase their consultation volume on OMC platforms. Furthermore, it not only enriches current trust-related research in the field of OMC, which has a certain reference significance for subsequent research on establishing trust in online doctor–patient relationships, but it also provides a reference for research concerning the antecedents of trust in general.

Prosaic Diction: Finding Patterns in the Words of Spenser’s View

Scholars have long noted the eccentric vocabulary of Spenser’s A View of the Present State of Ireland, primarily with an eye toward glossing words unfamiliar outside of a contemporary Irish context. This essay steps back from consideration of individual words to ponder what can be learned from word frequencies, primarily focusing on what the tools of corpus linguistics can tell us about the View and especially the View in relation to Spenser’s poetry. What words are most common in the View? What words in the View are most likely (or least likely) to occur in Spenser’s poetry? Is the vocabulary of Eudoxus similar to or notably different from the vocabulary of Irenius? What parts of Spenser’s poetic corpus have the greatest (or least) affinity, vocabulary-wise, with the View? This essay answers those questions and argues that linguistic analysis must go hand-in-hand with traditional close reading in order to draw conclusions from those answers.

Evaluating Frequency of words and Word Cloud from Astrological sentiments using NLP

The identification of interest/disinterest over a notion is having a huge demand in the current competitive data analytical world. For example, the customer preferences in various seasons, approximate visitors to a tourist place based on scenarios like weather and special occasions in the place, and so on. While giving an opinion on any concept, natural language in form of sentences/words/symbols/ratings plays a vital role. Depends upon the context and usage of natural language, captured opinions can be interpreted as either in a positive or negative sense. The terminology used for providing the opinions is used for analysing the data in an easy way. The evaluation of the word frequencies and word cloud are identified accurately, only after a keen analysis of the collected opinions. The Term-Document Matrix is one of the techniques that identify the frequency of words in each and every document/row in the given dataset, which can be used to generate the word cloud. In this paper to identify the frequency of words from the opinions given by multi-domain personalities on Astrology, distinct Natural Language Processing (NLP) techniques are used. A word cloud can also be generated from the set of words used for the astrological dataset.