Search

In the context of a globalized world where travel enthusiasts seek personalized recommendations for their favourite destinations, the study delves into sentiment analysis and travel recommendation systems. While previous research has explored various aspects of tourism destination selection, this work explores the use of star ratings to create sentiment lexicons tailored to specific domains. However, a notable limitation is the absence of a comprehensive investigation into the effectiveness of sentiment analysis techniques, in conjunction with star ratings, in accurately capturing review sentiment. This article aims to address this limitation by introducing a novel model that combines explicit sentiment scores and star ratings to predict optimal travel destinations based on user preferences. The model collects data from TripAdvisor but faces challenges related to noisy and non-informative elements such as HTML tags. To streamline the categorization process, preprocessing techniques like tokenization, stemming, and stop-word removal are applied. The study leverages Latent Dirichlet Allocation (LDA) topic modelling to extract user choice topics from the collected review data. Additionally, Correlated Topic Modeling (CTM) is employed to capture correlations between latent topics. The Morphological Linear Neural Network (MLNN) model is introduced to generate sentiment scores for textual content. These scores are then combined with star ratings from reviews to determine the most suitable destination. Furthermore, the study predicts average cumulative ratings by considering projected emotion scores and star ratings through the cumulative gain model. Implementation is carried out using Python software on a dataset comprising 67,871 samples. Evaluation metrics, including an F1-score of 89%, precision of 86%, and recall of 87%, indicate high performance in sentiment classification. The model exhibits an accuracy of approximately 95% and an RMSE value of 0.287, affirming its efficiency in polarity classification. Comparative analyses against state-of-the-art methods demonstrate the proposed model's superiority in terms of accuracy, precision, and recall. The practical implications of this model are underscored by its successful implementation and impressive evaluation results, highlighting its potential for enhancing personalized travel recommendations. [ABSTRACT FROM AUTHOR]

This article investigates the dissipation speed of positive and negative news in a geopolitical context. We perform a sentiment analysis of geopolitical news and measure the gamma of the corresponding sentiment scores per time unit in order to compare the travel speed of news with positive sentiment scores with news having negative sentiment scores. While prospect theory suggests that bad news is perceived as more impactful than good news, we show that this does not necessarily hold for the travel speed of news. On the contrary, we find that good news linked to keywords, which have usually a negative association, travel faster than bad news, and vice versa; a seeming repudiation of folk wisdom. Since our use cases were geopolitical crises, we associate phrases connected with conflict or the potential for conflict to have a broadly negative association. The implications of our insights suggest that the dissipation speed of news can be improved by framing and releasing positive news about events or entities with a negative association.

This study analyzes the effect of foodborne outbreaks that occurred in 2006 and 2008 in the peanut butter industry across the United States. The objective of this study was to estimate the demand and pricing conduct in the peanut butter industry under the salmonella outbreaks. The study applied a random coefficients multinomial logit demand for differentiated peanut butter brands. With own and cross-price elasticities and cost parameters corresponding to those products' attributes, the study analyzes the effect of a foodborne outbreak on consumers' behavior and manufacturers' pricing performance. Furthermore, this study used the demand estimates to measure the market power of peanut butter brands. Consumers react negatively to price in all cities, but the other taste parameter estimates for calorie, fat, sugar, and protein had a wide distribution, depending on consumers’ demographics. For pricing conduct, the cities indicated higher Lerner indices when the city shifted the pricing conduct.

This article investigates the dissipation speed of positive and negative news in a geopolitical context. We perform a sentiment analysis of geopolitical news and measure the gamma of the corresponding sentiment scores per time unit in order to compare the travel speed of news with positive sentiment scores with news having negative sentiment scores. While prospect theory suggests that bad news is perceived as more impactful than good news, we show that this does not necessarily hold for the travel speed of news. On the contrary, we find that good news linked to keywords, which have usually a negative association, travel faster than bad news, and vice versa; a seeming repudiation of folk wisdom. Since our use cases were geopolitical crises, we associate phrases connected with conflict or the potential for conflict to have a broadly negative association. The implications of our insights suggest that the dissipation speed of news can be improved by framing and releasing positive news about events or entities with a negative association. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Jilin University (Science Edition) / Jilin Daxue Xuebao (Lixue Ban) is the property of Zhongguo Xue shu qi Kan (Guang Pan Ban) Dian zi Za zhi She and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Recommendation systems in travel applications have a purpose to provide custom-made results to travelers while making a travel plan. These recommendation systems should be adaptable if user preferences change dynamically. To get custom-made results, the recommendation systems should be provided with traveler’s interests such as traveler’s specifications, preferences concerning destinations, type of activities they are very much interested to do in their travel plan. However, current recommendation systems are unable to fetch required features from travelers and destination places. Moreover, current systems are lacking to recommend destination places by considering social interest and their experience (i.e. recommendations by considering many traveler’s interests, for example, when two travelers interest matches the places visit by the first traveler can be suggested to the second traveler or vice-versa and travelers experience concerning particular destination place). To address the issues and problems of the current system, we propose and implement a tourist recommendation system which is termed as Average Cumulative Rating (ACR) that supports the extraction of rating and experience which is in the form of text description. The overall score is computed based on rating and traveler experience and feed to the traditional Matrix Factorization (MF) technique for providing custom results for travelers.

Abstract This research paper presents a novel approach for recommending products to customers based on their cared aspects by performing sentiment analysis on customer feedback. The proposed approach utilizes the WordNet database to identify and extract aspects from customer reviews and feedback, and then applies sentiment analysis techniques to determine the sentiment associated with each aspect. The resulting sentiment scores are then used to generate personalized product recommendations that align with the customer’s preferences and priorities. Here we extract the comments from an e-commerce website that is Amazon, and we then choose the most cared aspects from those comments. The dataset is publicly available online which contains reviews of each product. The chosen most cared aspects are price, colour, battery, and screen. These cared aspects are keywords that shopping online and recommending, will help to categorize the comments based on price, colour, battery, and screen. After categorizing the comments, it will be defined as the set of explicit comments. After an explicit comment set is defined, sentiment analysis is performed to systematically identify the interest of the customer through comments. Here the comments are classified into the polarity of given texts in an explicit comment set into positive, negative, and neutral. Finally, scores were calculated for all brands which will help to recommend the product.

This research paper presents a novel approach for recommending products to customers based on their cared aspects by performing sentiment analysis on customer feedback. The proposed approach utilizes the WordNet database to identify and extract aspects from customer reviews and feedback, and then applies sentiment analysis techniques to determine the sentiment associated with each aspect. The resulting sentiment scores are then used to generate personalized product recommendations that align with the customer's preferences and priorities. Here we extract the comments from an e-commerce website that is Amazon, and we then choose the most cared aspects from those comments. The dataset is publicly available online which contains reviews of each product. The chosen most cared aspects are price, colour, battery, and screen. These cared aspects are keywords that shopping online and recommending, will help to categorize the comments based on price, colour, battery, and screen. After categorizing the comments, it will be defined as the set of explicit comments. After an explicit comment set is defined, sentiment analysis is performed to systematically identify the interest of the customer through comments. Here the comments are classified into the polarity of given texts in an explicit comment set into positive, negative, and neutral. Finally, scores were calculated for all brands which will help to recommend the product. [ABSTRACT FROM AUTHOR]

Recommendation systems in travel applications have a purpose to provide custom-made results to travelers while making a travel plan. These recommendation systems should be adaptable if user preferences change dynamically. To get custom-made results, the recommendation systems should be provided with traveler's interests such as traveler's specifications, preferences concerning destinations, type of activities they are very much interested to do in their travel plan. However, current recommendation systems are unable to fetch required features from travelers and destination places. Moreover, current systems are lacking to recommend destination places by considering social interest and their experience (i.e. recommendations by considering many traveler's interests, for example, when two travelers interest matches the places visit by the first traveler can be suggested to the second traveler or vice-versa and travelers experience concerning particular destination place). To address the issues and problems of the current system, we propose and implement a tourist recommendation system which is termed as Average Cumulative Rating (ACR) that supports the extraction of rating and experience which is in the form of text description. The overall score is computed based on rating and traveler experience and feed to the traditional Matrix Factorization (MF) technique for providing custom results for travelers. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Sentiment analysis is the process of identifying and categorising the opinions expressed by human utterances through computational techniques using natural language processing. The present work focuses on a case study to develop a clinical decision support system for personalized therapy process using aspect-based sentiment analysis. The process is carried out on a drug review data in order to determine whether the patient’s behaviour towards a medicine, product, treatment etc is positive, negative or neutral using NLP techniques. The polarities obtained are compared for further analysis of the patient reviews for the better clinical decision system. Machine learning methods are also used for classification of the drug review data to compare the sentiment scores. The prominent statistical sklearn models used are support vector machines (SVM), Random Forest Classification, LinearSVC, MultinomialNB. SVM algorithm is found to perform better compared to other in terms of accuracy.

Making investment decisions by utilizing sentiment data from social media (SM) is starting to become a more tangible concept. There has been a broad investigation into this field of study over the last decade, and many of the findings have promising results. However, there is still an opportunity for continued research, firstly, in finding the most effective way to obtain relevant sentiment data from SM, then building a system to measure the sentiment, and finally visualizing it to help users make investment decisions. Furthermore, much of the existing work fails to factor SM metrics into the sentiment score effectively. This paper presents a novel prototype as a contribution to the field of study. In our work, a detailed overview of the topic is given in the form of a literature and technical review. Next, a prototype is designed and developed using the findings from the previous analysis. On top of that, a novel approach to factor SM metrics into the sentiment score is presented, with the goal of measuring the collective sentiment of the data effectively. To test the proposed approach, we only used popular stocks from the S&P500 to ensure large volumes of SM sentiment was available, adding further insight into findings, which we then discuss in our evaluation. [ABSTRACT FROM AUTHOR]

There has been a substantial amount of online discussion regarding the COVID - 19 pandemic. This perpetual restoration transition due to coronavirus disease has led to discussions on communal, fiscal, emotional and mental gratification of human beings. The disease has transformed the physical mode of communication among people to an online mode completely, involving greater use of emojis. Emojis are used extensively with text to express health conditions, prayers, ambulance, soaps, police, danger, facial expressions, sentiments, etc. To the best of our familiarity, the proposed work focuses on the importance of emojis for expressing sentiments. In this paper, the online document of 650 personages consisting of 1, 68,548 (what is this number?) tweets without COVID - 19 terminologies and 67,819 tweets dataset sample of COVID - 19 terminologies have been explored. The portrayal of emotions via emojis plays an important role. This promoted us to contribute a framework to categorize the numerous social media documents in to major categories: 'Online Document Content Class, ODCC' i.e., categorizing the different social media documents as text only, emoji only, and both text and emoji. This classification has been strengthened by analyzing the tweets of three major regions across the world. The hypothesis testing identifies the significance of emojis in the sentiment analysis during COVID along with superior productive way of tweets categorization. The results illustrate that online users of European region used the emojis most. The proposed approach presents precision of social media expression sentiment score and polarity evaluation is completely accomplished by considering text with emojis as well. [ABSTRACT FROM AUTHOR]

Sentimental Analysis has grown as a significant opinion strategy in the field of online media due to quick information development and internet technologies. This research will play an important role for recommendation of best airline for Indian passengers to prefer the appropriate airline for their journey and also useful for the Indian ministry of aviation. In this study we have gathered different tiny texts called comments from different social media traveling websites using webharvy data fetcher scraping tool related to six top rated Indian airlines. The main problem with airline tweet SA (sentimental analysis) is determining the best sentiment classifier for appropriately classifying the tweets. VADER model has used sentiment ratings to connect lexical characteristics to emotion intensities. In this research, a Hybrid model integrated Adaboost approach (HMIAA) has proposed, which combines the basic learning classifier SVM with the forward-learning ensemble method Gradient Boosted Tree to form a single robust classifier or model, with the objective of improving SCT (sentimental classification technique) efficiency (performance) and accuracy. The findings reveal that the suggested hybrid approach integrating Adaboost technique outperforms other basic classifiers. After completion of sentimental analysis of all datasets we can recommend the passengers for the best airline. [ABSTRACT FROM AUTHOR]

Sentiment analysis is the process of identifying and categorising the opinions expressed by human utterances through computational techniques using natural language processing. The present work focuses on a case study to develop a clinical decision support system for personalized therapy process using aspect-based sentiment analysis. The process is carried out on a drug review data in order to determine whether the patient's behaviour towards a medicine, product, treatment etc is positive, negative or neutral using NLP techniques. The polarities obtained are compared for further analysis of the patient reviews for the better clinical decision system. Machine learning methods are also used for classification of the drug review data to compare the sentiment scores. The prominent statistical sklearn models used are support vector machines (SVM), Random Forest Classification, LinearSVC, MultinomialNB. SVM algorithm is found to perform better compared to other in terms of accuracy. [ABSTRACT FROM AUTHOR]

This study conducted a holistic analysis of selected public-led regeneration projects carried out in different ways in rural and fishing villages in Korea, in line with current trends based on place-keeping theory, which reflects the long-term perspective of the project as a frame. This study identified the mechanisms and characteristics revealed in the planning process of the cases. Through an analysis of the discourse of the governing bodies, it also examined their perceptions and issues regarding the projects, finding that the different objectives of the projects and differences in the members leading the governance had different effects on the planning of the regeneration project. In this process, this study found distorted place-keeping elements: (1) The final design tends to be uniform rather than reflecting regional specificity. (2) As the investment in profit-making facilities was limited to one's own expense, funding was limited. (3) Asymmetry of partnership occurred due to the local community's insecurity following the adjustment of the plan. (4) In order to maintain a long-term governance system, a group of regionally friendly and responsible professionals was required. [ABSTRACT FROM AUTHOR]

Today YouTube is the first one application when the people need to learn something this is due to the robust service of the YouTube. Every second 500Hours video uploaded on the YouTube. On the one side this huge data is so big edge for YouTube but on the other side this is the big challenge for YouTube to provide efficient and effective search results for each user. People when search on the YouTube they are facing the difficulty to find the best video matched with their required content the only way to find the quality of the video is user feedback in term of comments but we also faced some problem too in comments most important are these two we focus 1.Huge comments 2.Multi-language comments for this problem our proposed method help the user to processes the all comments into the single English language and find the sentiment of the each video category and one the basis of the polarity score we find the best video tutorial and also compare the polarity results with and without our proposed method the results shows the method is effective and efficient.

Abstract Analyzing and understanding Internet news are important for many applications, such as market sentiment investigation and crisis management. However, it is challenging for users to interpret a massive amount of unstructured text, to dig out its accurate meaning, and to spot noteworthy news events. To overcome these challenges, we propose a novel visualization-driven approach for analyzing news text. We first collect Internet news from different sources and encode sentences into a vector representation suitable for input to a neural network, which calculates a sentiment score, to help detect news event patterns. A subsequent interactive visualization framework allows the user to explore the development of and relationships between Internet news topics. In addition, a method for detecting news events enables users and domain experts to interactively explore the correlations between market sentiment, topic distribution, and event patterns. We use this framework to provide a web-based interactive visualization system. We demonstrate the applicability and effectiveness of our proposed system using case studies involving blockchain news.

Making investment decisions by utilizing sentiment data from social media (SM) is starting to become a more tangible concept. There has been a broad investigation into this field of study over the last decade, and many of the findings have promising results. However, there is still an opportunity for continued research, firstly, in finding the most effective way to obtain relevant sentiment data from SM, then building a system to measure the sentiment, and finally visualizing it to help users make investment decisions. Furthermore, much of the existing work fails to factor SM metrics into the sentiment score effectively. This paper presents a novel prototype as a contribution to the field of study. In our work, a detailed overview of the topic is given in the form of a literature and technical review. Next, a prototype is designed and developed using the findings from the previous analysis. On top of that, a novel approach to factor SM metrics into the sentiment score is presented, with the goal of measuring the collective sentiment of the data effectively. To test the proposed approach, we only used popular stocks from the S&P500 to ensure large volumes of SM sentiment was available, adding further insight into findings, which we then discuss in our evaluation.

Hotel reviews play a vital role in tourism recommender system. They should be analyzed effectively to enhance the accuracy of recommendations which can be generated either from crisp ratings on a fixed scale or real sentiments of reviews. But crisp ratings cannot represent the actual feelings of reviewers. Existing tourism recommender systems mostly recommend hotels on the basis of vague and sparse ratings resulting in inaccurate recommendations or preferences for online users. This paper presents a semantic approach to analyze the online reviews being crawled from tripadvisor.in. It discovers the underlying fuzzy semantics of reviews with respect to the multiple criteria of hotels rather than using the crisp ratings. The crawled reviews are preprocessed via data cleaning such as stopword and punctuation removal, tokenization, lemmatization, pos tagging to understand the semantics efficiently. Nouns representing frequent features of hotels are extracted from pre-processed reviews which are further used to identify opinion phrases. Fuzzy weights are derived from normalized frequency of frequent nouns and combined with sentiment score of all the synonyms of adjectives in the identified opinion phrases. This results in fuzzy semantics which form an ideal representation of reviews for a multi-criteria tourism recommender system. The proposed work is implemented in python by crawling the recent reviews of Jaipur hotels from TripAdvisor and analyzing their semantics. The resultant fuzzy semantics form a manually tagged dataset of reviews tagged with sentiments of identified aspects, respectively. Experimental results show improved sentiment score while considering all the synonyms of adjectives. The results are further used to fine-tune BERT models to form encodings for a query-based recommender system. The proposed approach can help tourism and hospitality service providers to take advantage of such sentiment analysis to examine the negative comments or unpleasant experiences of tourists and making appropriate improvements. Moreover, it will help online users to get better recommendations while planning their trips. [ABSTRACT FROM AUTHOR]

Analyzing and understanding Internet news are important for many applications, such as market sentiment investigation and crisis management. However, it is challenging for users to interpret a massive amount of unstructured text, to dig out its accurate meaning, and to spot noteworthy news events. To overcome these challenges, we propose a novel visualization-driven approach for analyzing news text. We first collect Internet news from different sources and encode sentences into a vector representation suitable for input to a neural network, which calculates a sentiment score, to help detect news event patterns. A subsequent interactive visualization framework allows the user to explore the development of and relationships between Internet news topics. In addition, a method for detecting news events enables users and domain experts to interactively explore the correlations between market sentiment, topic distribution, and event patterns. We use this framework to provide a web-based interactive visualization system. We demonstrate the applicability and effectiveness of our proposed system using case studies involving blockchain news. [ABSTRACT FROM AUTHOR]