Predicting drug target interactions using meta-path-based semantic network analysis.

BACKGROUND: In the context of drug discovery, drug target interactions (DTIs) can be predicted based on observed topological features of a semantic network across the chemical and biological space. In a semantic network, the types of the nodes and links are different. In order to take into account the heterogeneity of the semantic network, meta-path-based topological patterns were investigated for link prediction. RESULTS: Supervised machine learning models were constructed based on meta-path topological features of an enriched semantic network, which was derived from Chem2Bio2RDF, and was expanded by adding compound and protein similarity neighboring links obtained from the PubChem databases. The additional semantic links significantly improved the predictive performance of the supervised learning models. The binary classification model built upon the enriched feature space using the Random Forest algorithm significantly outperformed an existing semantic link prediction algorithm, Semantic Link Association Prediction (SLAP), to predict unknown links between compounds and protein targets in an evolving network. In addition to link prediction, Random Forest also has an intrinsic feature ranking algorithm, which can be used to select the important topological features that contribute to link prediction. CONCLUSIONS: The proposed framework has been demonstrated as a powerful alternative to SLAP in order to predict DTIs using the semantic network that integrates chemical, pharmacological, genomic, biological, functional, and biomedical information into a unified framework. It offers the flexibility to enrich the feature space by using different normalization processes on the topological features, and it can perform model construction and feature selection at the same time.

Denotation and connotation in public representation: Semantic network analysis of Hwang supporters' internet dialogues.

This article analyzes the internet discourses of Korean people who supported Hwang Woo Suk despite the disclosure of his scientific misconduct. During the controversial period, those who supported Hwang constructed a narrative of a fallen hero trapped by jealous rivals and an "unjust" society. The supporters' dramatized discourses compete with expert opinions of Seoul National University's Audit Board and prosecutors that investigated the scientific fraud. By introducing and applying an innovative method of semantic network analysis, this study explores how the supporters represent their personal concerns in daily life and latent social problems in South Korea, as well as the failure of science communication. In short, the supporters' internet representations connote concerns in daily life that motivated their sympathy and activism for Hwang.

Meditation as panacea: A longitudinal semantic network analysis of meditation coverage in campus newspapers from 1997-2018.

OBJECTIVE: Media framing of health issues reflects public opinion and impacts readers' perceptions and behavior. This study examines how meditation - a recommended stress coping strategy for college students - is framed in campus newspapers from 1997-2018. PARTICIPANTS: A total of 494 articles were analyzed. METHODS: Semantic network analysis was used to automatically detect frames and the longitudinal trend. RESULTS: Five major frames emerged: (1) building a meditation community within a campus community, (2) meditation benefits, (3) yoga for enhancing mind and body awareness, (4) meditation techniques, and (5) secularizing meditation on campus. There is a shift in coverage from interest in religion to secular views of health benefits throughout the years. Discussions of adverse effects that have emerged from the literature were entirely absent. CONCLUSIONS: The trend of secularizing meditation practices on college campuses is evident. Emphasizing the techniques and benefits could encourage participation and build a learning community.

Analyzing Online Reviews to Uncover Customer Satisfaction Factors in Indian Cultural Tourism Destinations.

Tourism to Indian heritage destinations has been on the rise due to the increasing demand for heritage tourism. Increasing customer satisfaction and promoting Indian culture require tourism businesses to understand factors influencing tourists' experiences and behavior towards these destinations. Therefore, this study analyzes four popular heritage tourist destinations in India by using online reviews collected from Google Travel. Data are refined, processed, and visualized using the R programming language and UCINET 6.0. Furthermore, we explore the fundamental framework and interconnections among these characteristics through the utilization of exploratory factor analysis and linear regression analysis with the assistance of the SPSS software package. Based on customer reviews obtained from Google Reviews, an analysis was conducted on 6618 reviews of four heritage tourism destinations in India. From the top 60 words, four clusters of words were created, including "Physical characteristic", "Cultural and historical link", "atmosphere", and "area". Through explanatory factor analysis and linear regression analysis, we found that Physical characteristic, Cultural and historical link, atmosphere, and area all play a significant role in customer satisfaction. This study provides heritage destination managers and Indian government with insights into which attributes impact customer satisfaction the most and offers valuable marketing insights. As a result of this study, we are able to gain a greater understanding of the Indian heritage tourism market, and in doing so, we provide businesses with implications on how to enhance customer service.

Comparation of differences in the performance of corporate social responsibility between Chinese and American pharmaceutical enterprises-based on corporate social responsibility report.

Objective: We compared Chinese and American pharmaceutical companies' corporate social responsibility (CSR) reports to determine their differences and to analyze the possible reasons for them. Methods: We took as a model the top 500 pharmaceutical companies from Torreya's (a global investment bank) list of the 1,000 most valuable pharmaceutical companies in the world. We then collected the 2020 corporate social responsibility reports of 97 Chinese and 94 American pharmaceutical companies. These reports were analyzed using software such as ROST Content Mining 6.0 and Gephi 0.92. Results: We formed a high-frequency word list, a semantic network diagram, and a high-frequency word centrality scale for the Chinese and American pharmaceutical corporate social responsibility reports. The Chinese pharmaceutical companies' corporate social responsibility reports formed a layout of "double centers and double themes," and the text paid more attention to the disclosure of environmental protection information. The American pharmaceutical companies formed a report presentation form of "three centers and two themes," focusing on corporate social responsibility information disclosures from the perspective of humanistic care. Discussion: The differences in between Chinese and American pharmaceutical companies' corporate social responsibility reports may be due to different corporate development strategies, regulatory requirements, social demands, and the concept of "corporate citizenship." This study makes recommendations for Chinese pharmaceutical companies to better fulfill their CSR at three levels: policy-making, company management, and society.

Analyzing the dynamics of social media texts using coherency network analysis: a case study of the tweets with the co-hashtags of #BlackLivesMatter and #StopAsianHate.

Introduction: This study examines the associations between time series, termed "coherency," using spectral analysis. Coherence squared, analogous to the squared correlation coefficient, serves as a metric to quantify the degree of interdependence and co-evolution of individual nodes. Methods: We utilized spectral analysis to compute coherence squared, unveiling relationships and co-evolution patterns among individual nodes. The resultant matrix of these relationships was subjected to network analysis. Results: By conducting a case study analyzing tweets associated with the co-hashtags #StopAsianHate and #BlackLivesMatter, we present a novel approach utilizing coherency network analysis to investigate the dynamics of social media text. Frequency domain analysis aided in calculating coherence squared, effectively illustrating the relationships and co-evolution of individual nodes. Furthermore, an analysis of the phase spectrum's slope facilitated the determination of time lag and potential causality direction between highly co-evolved node pairs. Discussion: Our findings underline the potential of coherency network analysis in comprehending the intricate dynamics of social media text. This approach offers valuable insights into how topics, sentiments, or movements manifest and evolve within the digital realm. Future research should explore diverse datasets and domains to broaden our understanding of this novel analytical technique.

Effect of daily new cases of COVID-19 on public sentiment and concern: Deep learning-based sentiment classification and semantic network analysis.

Aim: This study explored the influence of daily new case videos posted by public health agencies (PHAs) on TikTok in the context of COVID-19 normalization, as well as public sentiment and concerns. Five different stages were used, based on the Crisis and Emergency Risk Communication model, amidst the 2022 Shanghai lockdown. Subject and Methods: After dividing the duration of the 2022 Shanghai lockdown into stages, we crawled all the user comments of videos posted by Healthy China on TikTok with the theme of daily new cases based on these five stages. Third, we constructed the pre-training model, ERNIE, to classify the sentiment of user comments. Finally, we performed semantic network analyses based on the sentiment classification results. Results: First, the high cost of fighting the epidemic during the 2022 Shanghai lockdown was why ordinary people were reluctant to cooperate with the anti-epidemic policy in the pre-crisis stage. Second, Shanghai unilaterally revised the definition of asymptomatic patients led to an escalation of risk levels and control conditions in other regions, ultimately affecting the lives and work of ordinary people in the area during the initial event stage. Third, the public reported specific details that affected their lives due to the long-term resistance to the epidemic in the maintenance stage. Fourth, the public became bored with videos regarding daily new cases in the resolution stage. Finally, the main reason for the negative public sentiment was that the local government did not follow the central government's anti-epidemic policy. Conclusion: Our results suggest that the methodology used in this study is feasible. Furthermore, our findings will help the Chinese government or PHAs improve the possible behaviors that displease the public in the anti-epidemic process.

Examining Crisis Communication Using Semantic Network and Sentiment Analysis: A Case Study on NetEase Games.

The mobile game "Immortal Conquest," created by NetEase Games, caused a dramatic user dissatisfaction event after an introduction of a sudden and uninvited "pay-to-win" update. As a result, many players filed grievances against NetEase in a court. The official game website issued three apologies, with mix results, to mitigate the crisis. The goal of the present study is to understand user feedback content from the perspective of Situational Crisis Communication Theory through semantic network analysis and sentiment analysis to explore how an enterprise's crisis communication strategy affects users' attitudes. First, our results demonstrate that the diminishing crisis communication strategies (excuse and justification) do not change players' negative attitudes. It was not a failure because it successfully alleviated the players' legal complaints and refocused their attention on the game itself. Second, the rebuild (apology & compensation) strategy was effective because it significantly increased the percentage of positive emotions and regenerated expectations for the game. The litigation crisis was identified within gamer communications with respect to Chinese gaming companies for the first time. Nevertheless, this does not indicate an increase in overall legal awareness among the larger Chinese population. It may only reflect greater legal awareness among Chinese online gamers. Fourth, gamers emphasized that they and enterprises should be equally involved when communicating with each other. Finally, in-game paid items should be reasonably priced, otherwise, they will drive users to competitors.

Framing matters but varies: a semantic network analysis of media representations of post-Fukushima food imports across three Chinese societies.

There is a remarkable gap between scientific experts and the nonscientific public regarding the safety of food imported from nuclear-contaminated areas in Japan. How socio-scientific issues such as post-Fukushima food imports are framed in media discourse may have effects on the way people perceive and reason about potential threats, and, in turn, influence government-initiated policies and regulations. In this study, semantic network analysis is performed to examine the diverse media representations of post-Fukushima food imports across information-seeking sources (mass media and search-based media) and three Chinese societies (Hong Kong, Mainland China, and Taiwan). We found that media representation of the crisis differs across sources and sociopolitical contexts. It is also discussed how these channel-specific and contextual factors may affect public opinion. This knowledge can enhance regulatory authorities' informed decision-making about food safety issues, guide crisis professionals' communication efforts, and call for a more context-sensitive approach to public health crisis management.

Excavating the social representations and perceived barriers of organ donation in China over the past decade: A hybrid text analysis approach.

Background: Organ donation has been claimed as a prosocial behavior to prolong the recipient's life and deliver great love. However, the supply-demand ratio of organs in China is highly unbalanced. Being entangled with multiple factors derived from individual and supra-individual levels, organ donation in China is important but sensitive. Previous scholars usually depended on obtrusive approaches to explore the facilitators and hindrances of organ donation, which is hard to discover genuine perceptions toward organ donation. Besides, relatively limited scholarly attention has been paid to what hampers organ donation in China. Objective: We intended to excavate the diversified social representations and perceived barriers to organ donation in China over the past decade. Method: Two kinds of text analysis methods-semantic network analysis and conventional content analysis, were applied to 120,172 posts from ordinary users on the Sina Weibo platform to address the research questions. Results: Regarding social representations, the "hope, understanding, and acceptance" of organ donation was the most pronounced one (34% of the whole semantic network), followed by "family story" (26%), "the procedure of organ donation in NGOs" (15%), "the practical value of organ donation" (14%), and "organ donation in the medical context" (11%). Regarding perceived barriers, a four-layer framework was constructed, including (1) the individual level, mainly about the fear of death and postmortem autopsy; (2) the familial level, which refers to the opposition from family members; (3) the societal level, which alludes to distrust toward medical institutions and the general society; (4) the cultural level, which covers religious-cultural concerns about fatalism. Conclusion: In concordance with prior works on social representations regarding organ donation, the current study also uncovered the coexistence of antithetical representations about organ donation-the longing for survival and the fear of death. This representation pair serves as the foundation of Chinese people's ambivalence. Besides, family-related narratives were dispersed over various representations, demonstrating the critical position of family support in organ donation. Moreover, the four-layer framework concerning donation barriers affords a reference for future empirical studies. The practical implications of this work are further discussed.

Some Assembly Required: Player Mental Models of Videogame Avatars.

In playing videogames, players often create avatars as extensions of agency into those spaces, where the player-avatar relationship (PAR) both shapes gameplay and is the product of gameplay experiences. Avatars are generally understood as singular bodies; however, we argue they are functional and phenomenological assemblages-networks of social and technological components that are internalized by players as networks of knowledge about the avatar. Different PARs are based on different internalizations (i.e., mental models) for what an avatar is and why it matters. Toward illuminating nuances in PARs, we examine the content and structure of players' internalizations of avatars as evidenced by descriptions of those digital bodies. Secondary analysis of N = 1,201 avatar descriptions parceled them by PAR type (avatars as asocial Objects, psychologically merged extensions of Me, hybrid me/other Symbiotes, and authentically social Other). Aggregated descriptions for each PAR type were subjected to semantic network analysis to identify patterns in salient avatar components, and then qualitatively compared across the four PARs. Results indicate component clusters that are universal to PARs (demographics and body features), common to three of four PARs (time, appearance, clothing, and player agency), and idiosyncratic to specific PARs (significance, character narratives, game dynamics, liminality, and gratifications). Findings signal the importance of theoretically engaging avatars as assemblages both (a) influenced by player-avatar sociality and (b) that contribute (in part and whole) to antecedents, processes, and effects of gameplay.

Semantic Network Analysis Using Construction Accident Cases to Understand Workers' Unsafe Acts.

Unsafe acts by workers are a direct cause of accidents in the labor-intensive construction industry. Previous studies have reviewed past accidents and analyzed their causes to understand the nature of the human error involved. However, these studies focused their investigations on only a small number of construction accidents, even though a large number of them have been collected from various countries. Consequently, this study developed a semantic network analysis (SNA) model that uses approximately 60,000 construction accident cases to understand the nature of the human error that affects safety in the construction industry. A modified human factor analysis and classification system (HFACS) framework was used to classify major human error factors-that is, the causes of the accidents in each of the accident summaries in the accident case data-and an SNA analysis was conducted on all of the classified data to analyze correlations between the major factors that lead to unsafe acts. The results show that an overwhelming number of accidents occurred due to unintended acts such as perceptual errors (PERs) and skill-based errors (SBEs). Moreover, this study visualized the relationships between factors that affected unsafe acts based on actual construction accident case data, allowing for an intuitive understanding of the major keywords for each of the factors that lead to accidents.

Studying attitudes towards vaccine hesitance and California law SB 277 in online discourse: A dataset and methodology.

This article presents data that are further analyzed and interpreted in "Shouting at Each Other into the Void: A Semantic Network Analysis of Vaccine Hesitance and Support in Online Discourse Regarding California Law SB277" [1]. This research modified snowball sampling, a technique usually used to generate chains of informants that illuminate the structure of social networks, to collect digital documents following a chain of web links and recommendations, thus illuminating the underlying social, technical, and linguistic structure of online discourse. The resulting documents were manually coded according to the attitude towards vaccines they represented and/or the position they took with regard to California Senate Bill 277, a vaccine mandate policy that banned all nonmedical exemptions from school immunization requirements. Each attitude category, as well as the dataset as a whole, was subjected to quantitative linguistic analysis to identify key words and phrases in the data according to the frequency with which they appeared. A combination of that technique and semantic network analysis were used to generate clusters of related words that could be used for qualitative and narrative analysis, as detailed in the companion paper. The data collection and analysis processes described here will be of use to researchers conducting mixed-method analysis of online discourse who want their data to reflect the potential information and digital resources available to individuals who attempt to inform themselves about a particular topic using Internet searches. The data presented here could be useful for anyone seeking deeper insight into the linguistic and narrative patterns surrounding online debates about vaccination, controversial government policies, or both.

Understanding the perceptions of Chinese women of the commercially available domestic and imported HPV vaccine: A semantic network analysis.

BACKGROUND: A domestic human papillomavirus (HPV) vaccine, Cecolin, that protects against HPV strains 16 and 18 was introduced to the Chinese market at a relatively low price in May 2020.This study has explored Chinese women's perceptions of both domestic and imported HPV vaccines, which differ in price and valency. METHODS: Sentiment analysis and semantic network analyses were performed based on a sample of 45,729 domestic HPV vaccine-related posts from females on the Sina Weibo between April 17 and May 2, 2020. The geographic distribution was also analyzed based on the users' locations, which were retrieved from the database. RESULTS: Most of the posts were positive and neutral (85%), although 15% were negative (e.g., expressions of anger, sadness, fear and disgust). Semantic analyses of the negative posts revealed that Chinese women generally had positive attitudes towards the HPV vaccine and were willing to be vaccinated. However, obvious geographical variations were identified. Women who lived in economically developed areas expressed a stronger desire to obtain imported quadrivalent or nonavalent vaccines due to concerns regarding effectiveness and quality. The women expressed disgust and anger mainly regarding difficulties in making an appointment, age restrictions for the nonavalent vaccine and gender restrictions. However, the population targeted by the domestic vaccine, namely women who lived in economically undeveloped areas and had relatively low incomes, had a low awareness of the HPV vaccine. CONCLUSION: Government should provide programs, which educate females that bivalent HPV vaccine can offer protection against the majority of high-risk HPV types. Increasing awareness of the domestic vaccine among the population in economically undeveloped areas and provision of free domestic bivalent HPV vaccination/screening for low-income high-risk women would help to prevent cervical carcinoma. This issue also depends on rebuilding trust and repairing damage to the relationship between government/domestic vaccine manufacturers and the public.

An exploration of the knowledge structure in studies on old people physical activities in Journal of Exercise Rehabilitation: by semantic network analysis.

Physical activity, a key component of maintaining health, is becoming an essential alternative in reducing medical expenses for the old people. This research was intended to analyze 51 research papers published in the Journal of Exercise Rehabilitation (JER) through semantic network analysis. The subjects of the study were the keywords that the authors of each paper used in journal search sites from 2013 to 2019. The present researcher analyzed the frequency, density, and centrality of the keywords of the indicators through semantic network analysis and then visualized them on the basis of findings using UCINET6 and the NetDraw program. Also, the researcher classified the hidden clusters by CONCOR (Convergence of iterated Correlations) analysis, which is a kind of cluster analysis. As a result, it was found that the keyword with the highest frequency was "exercise," followed by "cognition, "physicalactivity," "old-women," "Korean," "fall," and "training." It was also found that most of the high-frequency keywords, such as "exercise," "cognition," "old-women," "program" and "depression" had high centrality. These keywords were classified into four clusters: (a) mental health research, (b) physical health research, (c) social behavior research, and (d) leisure efficacy research. This suggests that the old people-related research papers published in the JER have derived effective methods of maintaining physical and mental health using scientific exercise programs, and especially address the effects of exercise intervention for old women.

Climatechange vs. Globalwarming: Characterizing Two Competing Climate Discourses on Twitter with Semantic Network and Temporal Analyses#.

Distinct perceptions of the global climate is one of the factors preventing society from achieving consensus or taking collaborative actions on this issue. The public has not even reached an agreement on the naming of the global concern, showing preference for either "climate change" or "global warming", and few previous studies have addressed these two competing discourses resulting from distinct climate concerns by differently linking numerous climate concepts. Based on the 6,662,478 tweets containing #climatechange or #globalwarming generated between 1 January 2009 and 31 December 2018, we constructed the semantic networks of the two discourses and examined their evolution over the decade. The findings indicate that climate change demonstrated a more scientific perspective and showed an attempt to condense climate discussions rather than diffuse the topic by frequently addressing sub-topics simultaneously. Global warming triggered more political responses and showed a greater connection with phenomena. Temporal analysis suggests that traditional political discussions were gradually fading in both discourses but more recently started to revive in the form of discourse alliance in the climate change discourse. The associations between global warming and weather abnormalitiessuddenly strengthened around 2012. Climate change is becoming more dominant than global warming in public discussions. Although two discourses have shown more similarities in the rank order of important climate concepts, apparent disagreements continue about how these concepts are associated. These findings lay the groundwork for researchers and communicators to narrow the discrepancy between diverse climate perceptions.

Shouting at each other into the void: A linguistic network analysis of vaccine hesitance and support in online discourse regarding California law SB277.

In 2015, California passed Senate Bill 277 and became the third state in the United States to ban all nonmedical exemptions from school immunization requirements, effectively prohibiting religious and personal belief exemptions. This attracted grassroots opposition and considerable debate among vaccine hesitant factions online. This mixed-methods study used quantitative linguistic analysis, semantic network analysis, and content analysis techniques to examine 2424 online documents drawn from newspapers, blogs, health websites, government information pages, web forums, personal websites, Facebook groups, among others. The study examined which words and phrases were used most frequently by vaccine skeptics, vaccine defenders, and more neutral media accounts to illuminate how groups with different attitudes towards vaccination discuss and disseminate information about vaccines and vaccine policy online. We proposed an innovative methodology for examining online discourse surrounding vaccine hesitance, as well as for studying the online dissemination of misinformation about vaccines. Our findings highlighted discrepancies in the narratives between what vaccine supporters believe causes vaccine skepticism and the issues that vaccine skeptics actually discuss within their own digital spaces. For example, in these exchanges, the importance of parental rights overshadowed that of children's rights; supporters of vaccines brought up autism in more distinct documents than skeptics do; distrust of government regulators and researchers seemed to unite vaccine skeptics and defenders; and politicians, doctors, and even celebrities often served as proxies in heated exchanges about factual evidence, believability, and the importance of expertise in public discourse.

Semantic Network Analysis Reveals Opposing Online Representations of the Search Term "GMO".

Making sound food and agriculture decisions is important for global society and the environment. Experts tend to view crop genetic engineering, a technology that can improve yields and minimize impacts on the environment, more favorably than the public. Because there is a causal relationship between public opinion and public policy, it is important to understand how opinions about genetically engineered (GE) crops are influenced. The public increasingly seeks science information on the Internet. Here, semantic network analysis is performed to characterize the presentation of the term "GMO (genetically modified organism)," a proxy for food developed from GE crops, on the web. Texts from three sources are analyzed: U.S. federal websites, top pages from a Google search, and online news titles. We found that the framing and sentiment (positive, neutral, or negative attitudes) of "GMO" varies across these sources. It is described how differences in the portrayal of GE food by each source might affect public opinion. A current understanding of the types of information individuals may encounter online can provide insight into public opinion toward GE food. In turn, this knowledge can guide teaching and communication efforts by the scientific community to promote informed decision-making about agricultural biotechnologies.

Computational drug repositioning using meta-path-based semantic network analysis.

BACKGROUND: Drug repositioning is a promising and efficient way to discover new indications for existing drugs, which holds the great potential for precision medicine in the post-genomic era. Many network-based approaches have been proposed for drug repositioning based on similarity networks, which integrate multiple sources of drugs and diseases. However, these methods may simply view nodes as the same-typed and neglect the semantic meanings of different meta-paths in the heterogeneous network. Therefore, it is urgent to develop a rational method to infer new indications for approved drugs. RESULTS: In this study, we proposed a novel methodology named HeteSim_DrugDisease (HSDD) for the prediction of drug repositioning. Firstly, we build the drug-drug similarity network and disease-disease similarity network by integrating the information of drugs and diseases. Secondly, a drug-disease heterogeneous network is constructed, which combines the drug similarity network, disease similarity network as well as the known drug-disease association network. Finally, HSDD predicts novel drug-disease associations based on the HeteSim scores of different meta-paths. The experimental results show that HSDD performs significantly better than the existing state-of-the-art approaches. HSDD achieves an AUC score of 0.8994 in the leave-one-out cross validation experiment. Moreover, case studies for selected drugs further illustrate the practical usefulness of HSDD. CONCLUSIONS: HSDD can be an effective and feasible way to infer the associations between drugs and diseases using on meta-path-based semantic network analysis.

Analysis of online patient experiences in a large public hospital′s internet hospital / 中华医院管理杂志

Objective:To analyze the online patient experiences in a public hospital′s internet hospital, and explore the influencing factors, for references for improving the online patient experiences and promoting the high-quality development of internet hospitals.Methods:Gender, age, visiting department, patient experience score, and evaluation text of patients in a public hospital′s internet hospital in 2022 were obtained. The patient experience scores were adopted the Likert 5-level scoring method. Intergroup comparisons were conducted by chi-square test and F-test. Word segmentation processing and word frequency statistics were used to extract high-frequency words in the evaluation text of dissatisfied patient experiences, and semantic network analysis on these high-frequency words was performed. Results:A total of 4 273 patients were included in this study, with a patient experience score of (4.1±1.6) points. Among them, 74.9% (3 199 cases) rated 5 points (very satisfied), and 19.5% (835 cases) rated 1 point (very dissatisfied). There was no significant difference in online patient experience scores among patients of different genders ( P>0.05), while patients of different ages or departments had different patient experience scores ( P<0.05); The top 10 high-frequently words of dissatisfied evaluation were doctor, answer, examination, limited help, ignoring, waste, refunding, registration fee, perfunctory, and closing.In the high-frequency semantic network of dissatisfied evaluations, high-frequency words such as doctor, answer, waste, examination, limited help, and ignoring were strongly correlated with each other. Conclusions:Most patients in an internet hospital were very satisfied with the online patient experience, but nearly 1/5 of the patients were very dissatisfied. The age and department affected the online patient experiences. The dissatisfied evaluations were mainly related to the attitude and professional competence of physicians, as well as the convenience of internet hospital platform and its diagnosis and treatment services.