Running a Sustainable Social Media Business: The Use of Deep Learning Methods in Online-Comment Short Texts

Abstract

With the prevalence of the Internet in society, social media has considerably altered the ways in which consumers conduct their daily lives and has gradually become an important channel for online communication and sharing activities. At the same time, whoever can rapidly and accurately disseminate online data among different companies affects their sales and competitiveness; therefore, it is urgent to obtain consumer public opinions online via an online platform. However, problems, such as sparse features and semantic losses in short-text online reviews, exist in the industry; therefore, this article uses several deep learning techniques and related neural network models to analyze Weibo online-review short texts to perform a sentiment analysis. The results show that, compared with the vector representation generated by Word2Vec’s CBOW model, BERT’s word vectors can obtain better sentiment analysis results. Compared with CNN, BiLSTM, and BiGRU models, the improved BiGRU-Att model can effectively improve the accuracy of the sentiment analysis. Therefore, deep learning neural network systems can improve the quality of the sentiment analysis of short-text online reviews, overcome the problems of the presence of too many unfamiliar words and low feature density in short texts, and provide an efficient and convenient computational method for improving the ability to perform sentiment analysis of short-text online reviews. Enterprises can use online data to analyze and immediately grasp the intentions of existing or potential consumers towards the company or product through deep learning methods and develop new services or sales plans that are more closely related to consumers to increase competitiveness. When consumers experience the use of new services or products again, they may provide feedback online. In this situation, companies can use deep learning sentiment analysis models to perform additional analyses, forming a dynamic cycle to ensure the sustainable operation of their enterprises.

A Semantic Analysis Method of Public Public Built Environment and Its Landscape Based on Big Data Technology: Kimbell Art Museum as Example

“…The method proposed in this study classified the effective data into three categories: human emotions (emotion), human behavior (behavior) and objects in the building that interact with people (object) and established a one-to-one corresponding relationship between visitors' reviews and the building. Following the Gephi network visualization logic mechanism, basic data analysis (overall word frequency analysis), temporal correlation analysis (analysis by month), spatial correlation analysis (spatial correlation analysis), and correlation analysis with others (Gephi correlation mechanism analysis) were performed on the three categories of reviews [24]. Data analysis covers the basic experience and attention of visitors, the influence of time factors such as seasons on the evaluation and landscape, and the overall relationship between the focus of the reviews in specific spaces and emotion, behavior, and object [25].…”

“…In the past 20 years, there have been more than one thousand articles on semantic network analysis [10], but the focused fields are limited: in addition to technology research, this method is mainly used in the landscape planning of scenic spots (accounting for Land 2024, 13, 655 2 of 15 24.6%) [11,12], whereas in the field of architectural science and engineering, related articles only account for 1.18% [13,14], and the research usually stops at the data sorting level, such as semantic classification and word frequency extraction, with no mature evaluation system that can establish connections between the complex network semantic data and actual usage based on a continuous logic [15,16]. This article summarizes a method of identifying problems from data and converting them into design guidance, making the structural evaluation open; therefore, the traditional top-bottom presupposition is replaced by bottom-top spontaneity, making up for the shortcomings of traditional methods such as lack of soft experience and visitors' spontaneity.…”