在数字化转型浪潮之下，党政机关、企事业单位充分利用新媒体开展宣传工作成为大势所趋，新媒体丰富生动的资源突破了传统宣传口径的局限性，也为宣传工作带来了前所未有的新挑战，如何使用信息化手段在新媒体环境下开展好宣传工作、提升新媒体内容的传播效果成为新媒体管理工作的重点和难点。通过挖掘海量数据信息从而对新媒体内容传播效果的影响因素和机理进行分析，能够为宣传工作者提供改进新媒体平台内容传播效果的思路及启示。

本文结合信息传播理论，将粉丝数量、发布时间、文本长度、是否包含视频、是否包含话题、内容主题与情感得分作为自变量构建了新媒体传播效果影响因素研究框架及模型，并将粉丝数量作为调节变量探究粉丝数对其他变量与传播效果之间关系的调节作用。本文将数据挖掘、深度学习等多种方法相结合，为使得研究贴近于高校及党政机关、企事业单位的实际应用，本文以15个共青团微博账号发布的202662条微博的真实数据为例，对主题分析、情感分析等具体问题提出了分析思路。考虑到使用传统LDA（Latent Dirichlet Allocation）模型提取内容文本主题的方法需要人为判断主题数目，本文提出使用eLDA（ensemble Latent Dirichlet Allocation）模型运用于新媒体内容主题挖掘，通过对LDA模型结果的集成来检测文本中的稳定主题。在获取文本情感倾向得分时，现有深度学习方法通常将整个句子送入模型中，对句子的整体情感倾向进行共同分析，在细粒度情感分析的思路下，本文构建了TR-BIBC-M（Topic Reinforced-BERT-IDCNN-BiLSTM-CRF-MMR）模型并提出了一种基于该模型的主题加强下的内容情感识别方法，利用主题词向量与实体词向量的相似度匹配实现主题增强下的实体词权重分配及语句情感赋分，得到句子针对所属主题的对应情感倾向。以新媒体传播效果影响因素模型为基础建立多元线性回归模型，将转发、评论和点赞数量作为因变量进行回归分析，并将数据源账号的粉丝数量对转发、评论、点赞数量及各影响自变量进行分层回归分析，检验新媒体传播效果影响因素的假设。

本文探讨了新媒体传播效果影响因素的分析路径与研究方法，所描述的问题及研究框架能够为信息传播、文本分析等相关研究提供思路，期望对党政机关及企事业单位新媒体宣传工作实践提供一定的帮助。

Under the tide of digital transformation, it has become a general trend for party and government organs, enterprises and institutions to make full use of new media to carry out propaganda work. The rich and vivid resources of new media break through the limitations of traditional propaganda work, and also bring unprecedented new challenges to it. How to use informationized means to carry out publicity work on the new media platforms and improve the communication effect of new media content has become the focus and difficulty of new media management. By mining massive data information to analyze the influencing factors and mechanisms of new media content communication effect, it can provide ideas and inspiration for propaganda workers to improve the content communication effect of new media platform.

Based on the theory of information communication, this paper constructs a research framework and model on factors affecting the communication effect of new media, taking the number of fans, release time, text length, whether videos are included, whether topics are included, content theme and emotional score as independent variables. Moreover, the number of fans is taken as a moderating variable to explore the moderating effect of the number of fans on the relationship between other variables and communication effect. This paper combines various methods such as data mining and deep learning. In order to make the research close to the practical application of universities, party and government organs, enterprises and institutions, this paper takes the real data of 202,662 microblogs published by 15 Weibo accounts of the Communist Youth League as an example, and puts forward analysis ideas on specific issues such as topic analysis and emotion analysis. Considering that the method of extracting content text topics using the traditional LDA (Latent Dirichlet Allocation) model requires human judgment of the number of topics, This paper proposes to use the ensemble Latent Dirichlet Allocation (eLDA) model to explore new media content themes, and to detect stable themes in text by integrating the results of the LDA model. When obtaining the score of text affective tendency, the existing deep learning methods usually send the whole sentence into the model and jointly analyze the overall affective tendency of the sentence. Under the thinking of fine-grained affective analysis, this paper constructs the TR-BIBC-M (Topic Reinforced-BERT-IDCNN-BiLSTM-CRF-MMR) model and proposes a content emotion recognition method based on the topic reinforcement of the model. The similarity matching between subject word vector and entity word vector is used to realize entity word weight allocation and sentence emotion assignment under topic enhancement, and the corresponding emotion tendency of sentences is obtained. A multiple linear regression model was established based on the model of factors affecting the effect of new media communication, and the number of retweets, comments and likes was taken as the dependent variables for regression analysis. Moreover, the number of fans of the data source account was stratified regression analysis on the number of retweets, comments, likes and each influencing independent variable to test the hypothesis of influencing factors of new media communication effect.

This paper discusses the analysis path and research method of the factors affecting the effect of new media communication, and the problems and research framework described can provide ideas for relevant research such as information communication and text analysis, and is expected to provide certain help for the practice of new media publicity in party and government organs, enterprises and institutions.

[1] Sungil Hong,Junghyun Kim,Eunhwa Yang. Automated Text Classification of Maintenance Data of Higher Education Buildings Using Text Mining and Machine Learning Techniques[J]. Journal of Architectural Engineering, 2022, 28(1).
[2] Yonghong Ma,Lingkai Kong,Chaoran Lin, et al. Research on the identification of generic technology of eco-friendly materials based on text mining[J]. Environmental Science and Pollution Research, 2022, 29(23): 35269-35283.
[3] Benjamin Garner,Corliss Thornton,Anita Luo Pawluk, et al. Utilizing text-mining to explore consumer happiness within tourism destinations[J]. Journal of Business Research, 2022, 139: 1366-1377.
[4] Gottipati Swetha,Guha Debashis. Analysing Tweets on COVID-19 Vaccine: A Text Mining Approach[C]//2022 IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC): IEEE, 2022.
[5] Cui Chao. Text Mining Of English Grammar Books In 19th ~ 20th Century[C]//2022 International Conference on Machine Learning and Knowledge Engineering (MLKE): IEEE, 2022.
[6] MyoungHoon Lee,Suhyeon Kim,Hangyeol Kim, et al. Technology Opportunity Discovery using Deep Learning-based Text Mining and a Knowledge Graph[J]. Technological Forecasting and Social Change, 2022, 180: 121718.
[7] Xintong Zhao,Steven Lopez,Semion Saikin, et al. Text to Insight: Accelerating Organic Materials Knowledge Extraction via Deep Learning[J]. Proceedings of the Association for Information Science and Technology, 2021, 58(1): 558-562.
[8] Sumit Madan,Fabian Julius Zimmer,Helena Balabin, et al. Deep Learning-based detection of psychiatric attributes from German mental health records[J]. International Journal of Medical Informatics, 2022, 161: 104724.
[9] Jia-Lang Xu,Ying-Lin Hsu. Analysis of agricultural exports based on deep learning and text mining[J]. The Journal of Supercomputing, 2022, 78(8): 10876-10892.
[10] Yerima Suleiman-Y.,To YiMin. A deep learning-enhanced botnet detection system based on Android manifest text mining[C]//2022 10th International Symposium on Digital Forensics and Security (ISDFS): IEEE, 2022: 1-6.
[11] Sivakumar C.,Sathyanarayanan D.,Karthikeyan P.,等. An Improvised Method for Anomaly Detection in social media using Deep Learning[C]//2022 International Conference on Electronics and Renewable Systems (ICEARS): IEEE, 2022: 1196-1200.
[12] Hui Xu,Yi Liu,Chi-Min Shu, et al. Cause analysis of hot work accidents based on text mining and deep learning[J]. Journal of Loss Prevention in the Process Industries, 2022, 76: 104747.
[13] 韩旭,李阳. 突发事件情境下社交媒体辟谣信息传播效果影响因素研究[J]. 情报理论与实践, 2022, 45(8): 97-103.
[14] 邸子桓,吕明臣. 信息生态视域下网络语言信息传播机制研究[J]. 情报科学, 2021, 39(1): 28-34.
[15] Stephen P. Sharp,Douglas G. Mackenzie,David S.Y. Ong, et al. Factors Influencing the Dissemination of Tweets at the American College of Surgeons Clinical Congress 2018[J]. The American Surgeon, 2020, 87(4): 520-526.
[16] Madhushika M.-D.,Ahangama Supunmali,Rajapaksha D.-A.. Analyzing the Impact of Social Media on Sinhala News Dissemination in Mass Media[C]//2022 2nd International Conference on Advanced Research in Computing (ICARC): IEEE, 2022.
[17] Zeyu Zheng,Huancheng Yang,Yang Fu, et al. Factors influencing message dissemination through social media[J]. Physical Review E, 2018, 97(6).
[18] Cheng Zhou,Kai Li,Yanhong Lu. Linguistic characteristics and the dissemination of misinformation in social media: The moderating effect of information richness[J]. Information Processing & Management, 2021, 58(6): 102679.
[19] 尹晓敏. 微博兴起背景下大学生思想政治教育的挑战与应对[J]. 思想教育研究, 2011, (2): 49-52.
[20] Guanghui Wang,Yufei Wang,Kaidi Liu, et al. Multidimensional influencing factors of public opinion information dissemination in social media: Evidence from Weibo dataset[J]. International Journal of Modern Physics B, 2019, 33(31): 1950375.
[21] 刘丽芳. 新媒体时代媒介素养融入高职思政教育思考[J]. 中国多媒体与网络教学学报(中旬刊), 2021, (9): 32-35.
[22] 魏萌,张博. 新浪微博“网红”的微博内容特征及传播效果研究[J]. 情报科学, 2018, 36(2): 88-94.
[23] Chen Chao,Chen Zuqin,Hu Tingkai,等. An Integrating Emotional Information and Topic Model Method for Text Topic Mining[C]//2021 International Conference on Networking, Communications and Information Technology (NetCIT): IEEE, 2021.
[24] Clamor Thomas-Daniel-S.,Solano Geoffrey-A.,Oco Nathaniel,等. Identification and Analysis of COVID-19-related Misinformation Tweets via Kullback-Leibler Divergence for Informativeness and Phraseness and Biterm Topic Modeling[C]//2022 International Conference on Artificial Intelligence in Information and Communication (ICAIIC): IEEE, 2022.
[25] Jian Jin,Qian Geng,Haikun Mou, et al. Author–Subject–Topic model for reviewer recommendation[J]. Journal of Information Science, 2018, 45(4): 554-570.
[26] Tontodimamma Alice,Gobbo Emiliano-del,Russo Vanessa,等. Studies in Classification, Data Analysis, and Knowledge Organization[M]. Cham: Springer International Publishing, 2020: 367-378.
[27] Ming Hong,Heyong Wang. Research on customer opinion summarization using topic mining and deep neural network[J]. Mathematics and Computers in Simulation, 2021, 185: 88-114.
[28] 田园,宫婷婷. 基于LDA模型的在线教学需求数据主题挖掘研究[J]. 情报科学, 2021, 039(9): 110.
[29] Eletter Shorouq-Fathi,Alqeisi Kholoud-Ibrahim,Elrefae Ghaleb-Awad. The Use of Topic Modeling in Mining Customers’ Reviews[C]//2021 22nd International Arab Conference on Information Technology (ACIT): IEEE, 2021.
[30] Saikumar Dhannuri,Subathra P.. Advances in Intelligent Systems and Computing[M]. Singapore: Springer Singapore, 2020: 153-167.
[31] 武帅,施奕,杨秀璋,等. 基于社交网络分析和LDA主题挖掘的短文本挖掘研究[J]. 现代电子技术, 2022, 045(20): 124.
[32] 李勇,欧志梅,黄格,等. 基于专利挖掘的数字文旅关键技术识别和趋势分析[J]. 图书馆论坛, 2023, 43(1): 121-130.
[33] S Soumya,V Pramod-K. Fine Grained Sentiment Analysis of Malayalam Tweets Using Lexicon Based and Machine Learning Based Approaches[C]//2021 4th Biennial International Conference on Nascent Technologies in Engineering (ICNTE): IEEE, 2021.
[34] Yen Show-Jane,Lee Yue-Shi,Lee Chung-Ken. Multi-class Sentiment Analysis[C]//2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI): IEEE, 2021.
[35] G Priyanka,T Vishnu-Viyaas,N Kathir-Vikram,等. Sentiment Analysis and Emoji Mapping[C]//2022 8th International Conference on Advanced Computing and Communication Systems (ICACCS): IEEE, 2022.
[36] Mohamed Gharzouli,Aimen Khalil Hamama,Zakaria Khattabi. Topic-based sentiment analysis of hotel reviews[J]. Current Issues in Tourism, 2021, 25(9): 1368-1375.
[37] Dellal-hedjazi Badiâa,Alimazighi Zaia. LSTM Network Learning for Sentiment Analysis[C]//Proceedings of the 24th International Conference on Enterprise Information Systems: SCITEPRESS - Science and Technology Publications, 2022.
[38] Cai Zisheng,Gao Han,Li Jiaye,等. Deep Learning Approaches on Multimodal Sentiment Analysis[C]//2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA): IEEE, 2022.
[39] Jie LENG,Xijin TANG. Graph Attention Networks for Multiple Pairs of Entities and Aspects Sentiment Analysis in Long Texts[J]. 系统科学与信息学报(英文), 2022, 10(3): 203-215.
[40] Sujata Rani,Parteek Kumar. Aspect-based Sentiment Analysis using Dependency Parsing[J]. Acm Transactions on Asian and Low-resource Language Information Processing, 2021, 21(3): 1-19.
[41] Shobana G.,Baskaran K.-R.,Yamunathangam D.. Aspect Based Sentiment Analysis for Customer Reviews[C]//2022 International Conference on Smart Technologies and Systems for Next Generation Computing (ICSTSN): IEEE, 2022.
[42] Lei Zhang,Shuai Wang,Bing Liu. Deep learning for sentiment analysis: A survey[J]. Wires Data Mining and Knowledge Discovery, 2018, 8(4).
[43] [43]Lasswell Harold-D.. The Structure and Function of Communication in Society[M]. New York: The Institute for Religious and Social Studies., 1948.
[44] Nianhua Ye,Jing Yu. Analysis of Current Situation of International Communication of Traditional Chinese Medicine Culture Assisted by Computer in the Age of Big Data---Taking Portugal as an Example[Z], 2021: 36.
[45] Ye Nianhua,Yu Jing. Analysis of Current Situation of International Communication of Traditional Chinese Medicine Culture Assisted by Computer in the Age of Big Data---Taking Portugal as an Example[C]//2021 World Automation Congress (WAC): IEEE, 2021.
[46] 嵇海香,任南. 基于流行三要素的视频热度影响因素研究——以B站为例[J]. 知识管理论坛, 2022, 7(1): 49-60.
[47] 孙振嘉,崔浩男,宋雪雁,等. 数字时代档案文献编纂成果传播影响因素研究[J]. 图书情报工作, 2020, 64(3): 12-22.
[48] 赵蓉英,李新来,明均仁. 融入情感特征的高校新媒体影响力评价研究——以高校官方微博为例[J]. 情报理论与实践, 2022, 45(6): 106-113.
[49] 柯赟. 新浪微博信息传播的影响因素分析与效果预测[J], 2016.
[50] 付宏,罗湘莹,杜智涛,等. 社会化媒体信息再传播的影响因素:内容、信源与卷入度[J]. 现代情报, 2021, 041(11): 31.
[51] Huilin Liu,Yao Li. Weibo Information Propagation Dissemination Based on User Behavior Using ELM[J]. Mathematical Problems in Engineering, 2015, 2015: 1-11.
[52] Shuiqing Yang,Chuanmei Zhou,Yuangao Chen. Do topic consistency and linguistic style similarity affect online review helpfulness? An elaboration likelihood model perspective[J]. Information Processing & Management, 2021, 58(3): 102521.
[53] Kai Li,Cheng Zhou,Xinyao Yu. Exploring the differences of users’ interaction behaviors on microblog: The moderating role of microblogger’s effort[J]. Telematics and Informatics, 2021, 59: 101553.
[54] Hofmann Thomas. Probabilistic latent semantic indexing[C]//Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval, New York, NY, USA: ACM, 1999.
[55] David Meir Blei,Andrew Ng,M. I. Jordan. Latent dirichlet allocation[J]. The Journal of Machine Learning Research, 2003.
[56] Tobias BRIGL. Extracting Reliable Topics using Ensemble Latent Dirichlet Allocation[D], 2019.
[57] Walaa Medhat,Ahmed Hassan,Hoda Korashy. Sentiment analysis algorithms and applications: A survey[J]. Ain Shams Engineering Journal, 2014, 5(4): 1093-1113.
[58] Lei Zhang,Shuai Wang,Bing Liu. Deep learning for sentiment analysis: A survey[J]. Wires Data Mining and Knowledge Discovery, 2018, 8(4).
[59] Yin Zhang,Rong Jin,Zhi-Hua Zhou. Understanding bag-of-words model: a statistical framework[J]. International Journal of Machine Learning and Cybernetics, 2010, 1(1): 43-52.
[60] Jerome R Bellegarda. Statistical language model adaptation: review and perspectives[J]. Speech Communication, 2004, 42(1): 93-108.
[61] Cavnar WB,Trenkle JM. N-Gram-Based Text Categorization[J], 2001.
[62] Bengio Y.,Réjean ducharme Pascal-Vincent-Christian-Jauvin. A Neural Probabilistic Language Model.[J], 2003.
[63] Mikolov Tomas,Chen KaiCorrado-GregDean-Jeffrey. Efficient Estimation of Word Representations in Vector Space[J], 2013.
[64] Lafferty J,A mccallum FCN-Pereira. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data[J], 2002.
[65] 邢文明,杨玲,陈继丽. 中美高校图书馆微博应用比较研究——基于新浪微博和推特的分析[J]. 图书情报工作, 2017, 61(19): 74-79.
[66] 孙传明,张海清. 非遗产品网络营销的影响因素研究——基于38个饮食类非遗技艺的分析[J]. 华中师范大学学报(自然科学版), 2022, 56(3): 428-436.
[67] 畅雅雯,杨波,高玥琳,等. 基于SEIR的微信公众号信息传播建模与分析[J]. 计算机科学, 2022, 49(4): 56-66.
[68] 冯小东,马捷,蒋国银. 社会信任、理性行为与政务微博传播:基于文本挖掘的实证研究[J]. 情报学报, 2019, 38(9): 954-965.
[69] 王兴元,刘赟. 如何调动微博粉丝的群体兴奋?企业微博内容类型与发布时间的影响研究[J]. 管理评论, 2022, 34(6): 162-172.
[70] 李瑾颉,吴联仁,齐佳音,等. 微博话题流行度统计分析及其影响因素研究[J]. 情报科学, 2017, 35(7): 138-141, 148.
[71] 赵文青,宗明刚. 学术期刊微信传播效果影响因素分析[J]. 中国科技期刊研究, 2016, 27(6): 611-616.
[72] 曾群,黄武英. 公共图书馆短视频传播效果影响因素组态路径研究——基于120个案例的模糊集定性比较分析[J]. 图书馆学研究, 2022, (7): 66-73.
[73] 李杨,柯瑞丰,周楠屿. 突发公共事件中我国主流媒体海外社交平台的叙事框架与传播效果研究[Z]: 新媒体与社会, 2022: 47-67.
[74] 蒙胜军,尚珏婷,张帆,等. 社交媒体中新冠疫情科学信息传播效果与危机应对策略选择影响因素研究——基于科学家群体相关热门微博文本的实证分析[J]. 图书情报工作, 2022, 66(13): 91-101.
[75] 郭小敏,徐学友. 科技学术期刊的短视频平台运营现状分析及策略探讨[J]. 编辑学报, 2022, 34(4): 443-448.
[76] 崔家勇,王锡苓. 社交媒体中的新冠疫苗信息框架及其对疫苗犹豫的影响——基于新浪微博的内容分析与在线控制实验[J]. 信息资源管理学报, 2022, 12(3): 165-180.
[77] Kunal Swani,George Milne,Brian P. Brown. Spreading the word through likes on Facebook[J]. Journal of Research in Interactive Marketing, 2013, 7(4): 269-294.
[78] 胡兵,冯采君. 认知视角下科普短视频传播效果的影响因素[J]. 科学学研究: 1-20.
[79] 韩德勋,黄杰. 社交媒体逻辑对新闻生产影响研究——基于“财新网”和“南方都市报”微信公众号的内容分析（2013—2020）[J]. 新闻记者, 2022, (8): 47-58.
[80] 李宏. 讲好警察故事：新媒体平台上的内容特点与传播效果——以中国警察网新浪微博为例[J]. 中国人民公安大学学报(社会科学版), 2022, 38(6): 119-130.
[81] 易明,张雪,李梓奇. 社交网络中辟谣信息传播效果的影响因素研究[J]. 情报科学, 2022, 40(5): 3-10, 18.
[82] 刘洋,董卓宁. 高校辅导员微信公众号传播效果的影响因素研究[J]. 思想教育研究, 2020, (11): 142-147.
[83] 肖亚龙,冯皓,朱承璋,等. 基于社会网络分析的重大自然灾害事件线上社会支持寻求与供给研究[J]. 情报杂志: 1-10.
[84] 李成蹊,吴芳,孙琦. 社交互动情境下的信息传播效果研究[J]. 管理工程学报: 1-13.
[85] 余红,余梦珑. 信息补贴与信息偶遇：复杂公共议题中科学传播框架嵌入研究[J]. 情报杂志, 2022, 41(4): 119-127.
[86] 孟庆涛,齐媛,侯金芹,等. 为担当民族复兴大任的时代新人培根铸魂——习近平总书记关于教育的重要论述学习研究之一[J]. 教育研究, 2022, 43(1): 11-22.
[87] 徐振祥. 新媒体_大学生思想政治教育的机遇与挑战[J]. 思想政治教育研究, 2007, (6): 64-66.
[88] 胡树祥,谢玉进. 大数据时代的网络思想政治教育[J]. 思想教育研究, 2013, (6): 60-62, 102.
[89] 汪頔. 新媒体对“90后”大学生思想政治教育的新挑战[J]. 思想教育研究, 2010, (1): 71-74.
[90] 钱文彬. 浅析新媒体与大学生思想政治教育[J]. 当代教育论坛(宏观教育研究), 2008, (6): 71-72.
[91] 刘淑慧. “互联网+课程思政”模式建构的理论研究[J]. 中国高等教育, 2017, (Z3): 15-17.
[92] 王海建. “00后”大学生的群体特点与思想政治教育策略[J]. 思想理论教育, 2018, (10): 90-94.
[93] 沈壮海. “大思政课”我们要善用之:思考与探索[J]. 思想政治教育研究, 2021, 37(3): 26-30.
[94] 许瑞芳,张宜萱. 沉浸式“大思政课”的价值意蕴及建构理路[J]. 思想理论教育导刊, 2021, (11): 83-88.
[95] 李厚锐. 智能媒体赋能高校思想政治教育创新探究[J]. 思想理论教育, 2022, (7): 96-101.
[96] 吴满意,景星维. 精准思政：内涵生成与结构演化[J]. 学术论坛, 2019, 42(5): 133-139.
[97] 李洁,廖小琴. 智媒时代思想政治教育话语发展的审视[J]. 思想教育研究, 2021, (7): 51-57.
[98] 崔建西,白显良. 智能思政：思想政治教育创新发展的新形态[J]. 思想理论教育, 2021, (10): 83-88.
[99] 于祥成,刘成. 微传播时代高校思想政治教育的理路转换、困境审思及实践进路[J]. 新疆师范大学学报(哲学社会科学版), 2022, 43(6): 47-55.
[100] 汤苗苗,谭文轶. 新媒体视域下大学生主流意识形态教育研究[J]. 学校党建与思想教育, 2021, (18): 85-87.
[101] 尹辉,王维平. 传播效果视域的高校社会主义核心价值观教学策略[J]. 思想教育研究, 2022, (7): 126-132.
[102] 蔡志鹏,路丙辉. 百年团史融入高校思想政治教育的三重维度[J]. 浙江理工大学学报(社会科学版), 2022, 48(5): 613-620.
[103] 陈强,张杨一,马晓悦,等. 政务B站号信息传播效果影响因素与实证研究[J]. 图书情报工作, 2020, 64(22): 126-134.
[104] Day Min-Yuh,Lee Chia-Chou. Deep learning for financial sentiment analysis on finance news providers[C]//2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM): IEEE, 2016.
[105] 官琴,邓三鸿,王昊. 中文文本聚类常用停用词表对比研究_官琴[J]. 数据分析与知识发现, 2017, 1(3): 72-80.
[106] Yin Zhang,Rong Jin,Zhi-Hua Zhou. Understanding bag-of-words model: a statistical framework[J]. International Journal of Machine Learning and Cybernetics, 2010, 1(1): 43-52.
[107] Akiko Aizawa. An information-theoretic perspective of tf–idf measures[J]. Information Processing & Management, 2003, 39(1): 45-65.
[108] T. K. Moon. The expectation-maximization algorithm[J]. Ieee Signal Processing Magazine, 1996, 13(6): 47-60.
[109] Pan CR,Qh wang BZ-Tang-L-Jiang-X-Huang-L-Wang-SO-Medicine-N-University-Shenzhen-C-Hospital. Chinese electronic medical record named entity recognition based on sentence-level Lattice-long short-term memory neural network[J], 2019.
[110] 许山山,史涯晴. 基于Bi-LSTM+CRF模型的航母情报实体识别方法应用[J]. 计算机时代, 2023, (1): 30-34.
[111] R. Collobert,J. Weston,L. Bottou, et al. Natural Language Processing (almost) from Scratch[P].
[112] Z. Huang,X. Wei,Y. Kai. Bidirectional LSTM-CRF Models for Sequence Tagging[J]. Computer Science, 2015.
[113] E. Strubell,P. Verga,D. Belanger, et al. Fast and Accurate Entity Recognition with Iterated Dilated Convolutions[J], 2017.
[114] 蒋翔,马建霞,袁慧. 基于BiLSTM-IDCNN-CRF模型的生态治理技术领域命名实体识别[J]. 计算机应用与软件, 2021, 38(3): 134-141.
[115] 冷建飞,高旭,朱嘉平. 多元线性回归统计预测模型的应用[J]. 统计与决策, 2016, (7): 82-85.
[116] 陈强,张杨一,马晓悦,等. 政务B站号信息传播效果影响因素与实证研究[J]. 图书情报工作, 2020, 64(22): 126-134.
[117] 宁海林,羊晚成. 重大突发公共卫生事件传播效果的影响因素实证分析——以卫健类抖音政务号为例[J]. 现代传播(中国传媒大学学报), 2021, 43(1): 147-151.
[118] 江美莲,邓艳昕,王玉琦. 影响文旅政务微博传播效果因素的实证探究——以“海昏侯”微博为例[J]. 出版广角, 2021, (8): 80-83.
[119] 张丽,李秀峰. 共青团中央抖音短视频的传播效果及影响因素分析[J]. 中国青年社会科学, 2022, 41(2): 30-42.
[120] 冯少荣,冯康巍. 基于统计分析方法的雾霾影响因素及治理措施[J]. 厦门大学学报(自然科学版), 2015, 54(1): 114-121.
[121] 孙玮晟. 高校B站官方UP号消息发布的现状及特点研究[J]. 科技传播, 2021, 13(11): 139-142.
[122] 刘政委,张伟峰,张新星,等. 政务微博地区影响力差异及影响因素分析——基于关系数据分析范式的经验证据[J]. 情报探索, 2021, (10): 81-86.
[123] 易明,张雪,李梓奇. 社交网络中辟谣信息传播效果的影响因素研究[J]. 情报科学, 2022, 40(5): 3-10, 18.
[124] 安璐,陈苗苗. 突发事件情境下政务微博信息发布有效性评估[J]. 情报学报, 2022, 41(7): 692-706.
[125] 张蒙,徐文贤. 高校官方微博用户信息参与行为影响因素研究——以黑龙江省19所高校为例[J]. 情报探索, 2022, (6): 80-84.
[126] 叶均玲,郑佩佩,苏比努尔·玉素甫,等. 武汉市政务微博传播效果评价与优化研究[J]. 情报探索, 2020, (12): 31-37.
[127] 许林玉,杨建林. 基于社会化媒体数据的学术社区知识共享行为影响因素研究——以经管之家平台为例[J]. 现代情报, 2019, 39(7): 56-65.