Analyzing the sentiments of people from social media content through text, speech, and images is becoming vital in a variety of applications. Many existing research studies on sentiment analysis rely on textual data, and similar to the sharing of text, users of social media share more photographs and videos. Compared to text, images are said to exhibit the sentiments in a much better way. So, there is an urge to build a sentiment analysis model based on images from social media. In our work, we employed different transfer learning models, including the VGG-19, ResNet50V2, and DenseNet-121 models, to perform sentiment analysis based on images. They were fine-tuned by freezing and unfreezing some of the layers, and their performance was boosted by applying regularization techniques. We used the Twitter-based images available in the Crowdflower dataset, which contains URLs of images with their sentiment polarities. Our work also presents a comparative analysis of these pre-trained models in the prediction of image sentiments on our dataset. The accuracies of our fine-tuned transfer learning models involving VGG-19, ResNet50V2, and DenseNet-121 are 0.73, 0.75, and 0.89, respectively. When compared to previous attempts at visual sentiment analysis, which used a variety of machine and deep learning techniques, our model had an improved accuracy by about 5% to 10%. According to the findings, the fine-tuned DenseNet-121 model outperformed the VGG-19 and ResNet50V2 models in image sentiment prediction.

/pdf/visual-sentiment-analysis-using-deep-learning-models-with-qypvmm9i.pdf

Visual Sentiment Analysis Using Deep Learning Models with Social Media Data

Online product sentiment analysis using random evolutionary whale optimization algorithm and deep belief network

In today's modern era, e-commerce is making headway through the process of bringing goods within everyone's grasp. Consumers are not even required to step out of the comfort of their homes for buying things, which makes it very convenient for them. Moreover, there is a wide variety of brands to choose from. Since more customers depend on online shopping platforms these days, the value of ratings is also growing. To buy these products, people rely solely on the reviews that are being provided about the products. To analyze these reviews, sentiment analysis needs to be performed, which can prove useful for both the buyers and the manufacturer. This paper describes the process of sentiment analysis and its requirements. In this paper, Amazon Review dataset 2018 has been used for carrying out our research and Long Short-Term Memory (LSTM) has been combined with word2vec representation, resulting in improving the overall performance. A gating mechanism was used by LSTM during the training process. The proposed LSTM model was evaluated on four performance measures: accuracy, precision, recall, and F1 score, and achieved overall higher results when compared with other baseline models.

/pdf/efficient-long-short-term-memory-based-sentiment-analysis-of-nkoixr19.pdf

Efficient Long Short-Term Memory-Based Sentiment Analysis of E-Commerce Reviews

Entrepreneurial role models are the forerunners on the path to entrepreneurship for college students, and they play a significant role in influencing college students’ entrepreneurship decisions. Entrepreneurship education in schools is an important tool for college students to develop entrepreneurial knowledge, ingenuity, and abilities. The main approach of building fuzzy systems is fuzzy integrated assessment, and it has a broad range of applications, including expert evaluation systems, quality control, performance assessment, weather forecasting, medical diagnosis, economic management, and psychological measurement. This research designs a fuzzy integrated evaluation system of university students’ entrepreneurial education using the environment, teaching process, and instructors’ team as the first-level indicators on the premise of defining the connotation of inventive and entrepreneurial skills. The article also uses the fuzzy integrated assessment method to conduct an empirical study and proposes countermeasures for the quality of innovative and entrepreneurial talents cultivation in terms of creating a good innovation environment in universities and encouraging students to actively participate in various innovative and entrepreneurial activities. The experimental results show that the half confidence of the fuzzy integrated assessment algorithm is 0.657, the retest confidence is 0.991, and the standard deviation of the 
 
 α
 
 coefficient among all the test subjects is 0.683, which indicates that it has good confidence. Therefore, the fuzzy integrated assessment method of college students’ entrepreneurial education in this study is a combination of quantitative and qualitative methods, which expresses and processes the subjective judgment of human in quantitative form, minimizes the drawbacks brought by personal subjective judgment, and makes the evaluation results more credible.

/pdf/exploring-the-fuzzy-integrated-assessment-of-college-317o2nig.pdf

Exploring the Fuzzy Integrated Assessment of College Students’ Education for Innovative Entrepreneurship under the Background of Internet+

PurposeThis research aimed to examine the role of cloud infrastructure capabilities of tourism small and medium-sized enterprises (SMEs) in the tourism supply chain, increasing the online consumption value of tourists.Design/methodology/approachThis study uses stratified random sampling. A value model was formulated, and the study distributed 2,000 surveys; 412 valid responses were received and analyzed using the structural equation modeling approach.FindingsThe cloud-based architecture provides tourism SMEs a competitive advantage in the dynamic tourism market and the ability to develop next-generation system capabilities while providing tourism SMEs with a new application foundation to adapt to the ever-changing tourism market.Originality/valueFor tourism SEMs, the cloud allows adjusting strategies and procedures for tourism supply chain management; this agility enables tourism SMEs to anticipate changes in the travel market and respond to changing consumer demands in the tourism industry.

Cloud infrastructure enhancing product competitive advantage of tourism SMEs on online consumption values of tourists

Recently, online shopping has turned into a mainstream means for users to purchase as well as consume with the upsurge development of Internet technology. User satisfaction can be improved effectively by doing Sentiment Analysis (SA) of a large quantity of user reviews on e-commerce platforms. It is still challenging to envisage the accurate sentiment polarities of the user reviews because of the changes in sequence length, textual order, along with complicated logic. This paper proposes a new optimized Machine Learning (ML) algorithm called the Local Search Improvised Bat Algorithm based Elman Neural Network (LSIBA-ENN) for the SA of online product reviews. The proposed work of SA encompasses ‘4’ major steps: i) Data Collection (DC), ii) preprocessing, iii) Features Extraction (FE) or Term Weighting (TW), Feature Selection (FS), and polarity or Sentiment Classifications (SC). Initially, the Web Scrapping Tool (WST) is utilized to extract the customer reviews of the products for which the data is gathered as of the E-commerce websites. Next, preprocessing is carried out on the web scrap extracted data. Those preprocessed data go through TW and FS for additional processing by means of Log Term Frequency-based Modified Inverse Class Frequency (LTF-MICF) and Hybrid Mutation based Earth Warm Algorithm (HMEWA). Lastly, the HM-EWA data is rendered to the LSIBA-ENN, which classifies the customer reviews’ sentiment as positive, negative, and neutral. For the performance analysis of the proposed and prevailing classifiers, ‘2’ yardstick datasets are taken. The outcomes exhibit that the LSIBA-ENN attains the best performance in SC when weighted against the existing top-notch algorithms. The observations of the reviewer are exact. The prevailing ENN proffers recall of 87.79 when utilizing the proposed LTF-MICF scheme, whereas ENN only achieve 83.55, 84.03, 85.48, and 86.04 of recall whilst utilizing W2V, TF, TF-IDF, and TF-DFS schemes respectively.

A machine learning-based sentiment analysis of online product reviews with a novel term weighting and feature selection approach

The customer enables online reviews, discusses product features and enhances the user's experiences in online activities Users generated product innovation and product reviews effect as market competition This research study explains deep learning, online reviews and product innovation empirical evidence used by mobile apps,Online reviews and product innovation are very important for every organization and firms to achieve a competitive advantage in a large business environment When the authors see past traditional history, customers are not involved in product creating and innovating processes Due to new technology changes, online systems and web 20 increase this ability,For this research purpose, the authors use different analytical software to measure the impact among variables This study is established on primary data; this study collected data from online customers and its users For data collection, the authors use some questionnaires, and these questions are filled from 200 respondents,This research study used data from the Google app store – Google product selling application – and gathered customers' online reviews Research found that customers' online reviews and deep learning positively and significantly influence product innovation through networking technology This research-based online mobile application and its research reviews found that organizations convert their own business online and effectively and efficiently enhance creditability,This research study used data from the Google app store Google product selling application and gathered customers' online reviews Research founded that customers' online reviews and deep learning are positively and significantly influence product innovation through networking technology This research-based online mobile application and its research reviews found that organizations convert their own business online and effectively and efficiently enhance creditability

Huiliang Zhao

Papers

A machine learning-based sentiment analysis of online product reviews with a novel term weighting and feature selection approach

Impact of online customer reviews and deep learning on product innovation empirical study on mobile applications