Mining User Interest in Microblogs with a User-Topic Model

Microblogs have become an important platform for people to publish,transform information and acquire knowledge.This paper focuses on the problem of discovering user interest in microblogs.In this paper,we propose a topic mining model based on Latent Dirichlet Allocation(LDA) named user-topic model.For each user,the interests are divided into two parts by different ways to generate the microblogs:original interest and retweet interest.We represent a Gibbs sampling implementation for inference the parameters of our model,and discover not only user's original interest,but also retweet interest.Then we combine original interest and retweet interest to compute interest words for users.Experiments on a dataset of Sina microblogs demonstrate that our model is able to discover user interest effectively and outperforms existing topic models in this task.And we find that original interest and retweet interest are similar and the topics of interest contain user labels.The interest words discovered by our model reflect user labels,but range is much broader.

A comparative study of information diffusion in weblogs and microblogs based on social network analysis

Purpose: This paper intends to explore a quantitative method for investigating the characteristics of information diffusion through social media like weblogs and microblogs.By using the social network analysis methods,we attempt to analyze the different characteristics of information diffusion in weblogs and microblogs as well as the possible reasons of these differences.Design/methodology/approach: Using the social network analysis methods,this paper carries out an empirical study by taking the Chinese weblogs and microblogs in the field of Library and Information Science(LIS) as the research sample and employing measures such as network density,core/peripheral structure and centrality.Findings: Firstly,both bloggers and microbloggers maintain weak ties,and both of their social networks display a small-world effect. Secondly,compared with weblog users,microblog users are more interconnected,more equal and more capable of developing relationships with people outside their own social networks. Thirdly,the microblogging social network is more conducive to information diffusion than the blogging network,because of their differences in functions and the information flow mechanism. Finally,the communication mode emerged with microblogging,with the characteristics of micro-content,multi-channel information dissemination,dense and decentralized social network and content aggregation,will be one of the trends in the development of the information exchange platform in the future.Research limitations: The sample size needs to be increased so that samples are more representative. Errors may exist during the data collection. Moreover,the individual-level characteristics of the samples as well as the types of information exchanged need to be further studied.Practical implications: This preliminary study explores the characteristics of information diffusion in the network environment and verifies the feasibility of conducting a quantitative analysis of information diffusion through social media. In addition,it provides insight into the characteristics of information diffusion in weblogs and microblogs and the possible reasons of these differences.Originality/value: We have analyzed the characteristics of information diffusion in weblogs and microblogs by using the social network analysis methods. This research will be useful for a quantitative analysis of the underlying mechanisms of information flow through social media in the network environment.

What is Discussed about COVID-19:A Multi-Modal Framework for Analyzing Microblogs from Sina Weibo without Human Labeling

Starting from late 2019,the new coronavirus disease(COVID-19)has become a global crisis.With the development of online social media,people prefer to express their opinions and discuss the latest news online.We have witnessed the positive influence of online social media,which helped citizens and governments track the development of this pandemic in time.It is necessary to apply artificial intelligence(AI)techniques to online social media and automatically discover and track public opinions posted online.In this paper,we take Sina Weibo,the most widely used online social media in China,for analysis and experiments.We collect multi-modal microblogs about COVID-19 from 2020/1/1 to 2020/3/31 with a web crawler,including texts and images posted by users.In order to effectively discover what is being discussed about COVID-19 without human labeling,we propose a unified multi-modal framework,including an unsupervised short-text topic model to discover and track bursty topics,and a self-supervised model to learn image features so that we can retrieve related images about COVID-19.Experimental results have shown the effectiveness and superiority of the proposed models,and also have shown the considerable application prospects for analyzing and tracking public opinions about COVID-19.

Research on the Use of Network Language in Chinese Government Microblogs

The emergence of government microblog not only widens the channels for the people to participate in politics,but also is of great significance for the government to understand public opinion and promote the process of political democratization.In recent years,the frequency of network language in Chinese government microblog has gradually increased.Taking the“Beijing release”official microblog as an example,this paper discusses the characteristics of network language,and puts forward some suggestions on the use of network language in government microblog:in terms of syllables,network language below three syllables should be selected to meet the requirements of short length of government microblog;In terms of part of speech,network terms such as nouns,verbs and adjectives can express emotional attitude and value judgment;In terms of emotion and style,emotional attitude forms such as intimacy,love and respect are selected.In addition,the norms of network language in government microblog can not be generalized.We should not only pay attention to the expression effect,but also set foot in multiple disciplines and fields.

Normalization of Homophonic Words in Chinese Microblogs

Homophonic words are very popular in Chinese microblog, posing a new challenge for Chinese microblog text analysis. However, to date, there has been very little research conducted on Chinese homophonic words normalization. In this paper, we take Chinese homophonic word normalization as a process of language decoding and propose an n-gram based approach. To this end, we first employ homophonic–original word or character mapping tables to generate normalization candidates for a given sentence with homophonic words, and thus exploit n-gram language models to decode the best normalization from the candidate set. Our experimental results show that using the homophonic-original character mapping table and n-grams trained from the microblog corpus help improve performance in homophonic word recognition and restoration.

Measuring the spreadability of users in microblogs

Message forwarding (e.g.,retweeting on Twitter.com) is one of the most popular functions in many existing microblogs,and a large number of users participate in the propagation of information,for any given messages.While this large number can generate notable diversity and not all users have the same ability to diffuse the messages,this also makes it challenging to find the true users with higher spreadability,those generally rated as interesting and authoritative to diffuse the messages.In this paper,a novel method called SpreadRank is proposed to measure the spreadability of users in microblogs,considering both the time interval of retweets and the location of users in information cascades.Experiments were conducted on a real dataset from Twitter containing about 0.26 million users and 10 million tweets,and the results showed that our method is consistently better than the PageRank method with the network of retweets and the method of retweetNum which measures the spreadability according to the number of retweets.Moreover,we find that a user with more tweets or followers does not always have stronger spreadability in microblogs.

Hashtag Recommendation Based on Multi-Features of Microblogs

Hashtag recommendation for microblogs is a very hot research topic that is useful to many applications involving microblogs. However, since short text in microblogs and low utilization rate of hashtags will lead to the data sparsity problem, it is difficult for typical hashtag recommendation methods to achieve accurate recommendation. In light of this, we propose HRMF, a hashtag recommendation method based on multi-features of microblogs in this article. First, our HRMF expands short text into long text, and then it simultaneously models multi-features （i.e., user, hashtag, text） of microblogs by designing a new topic model. To further alleviate the data sparsity problem, HRMF exploits hashtags of both similar users and similar microblogs as the candidate hashtags. In particular, to find similar users, HRMF combines the designed topic model with typical user-based collaborative filtering method. Finally, we realize hashtag recommendation by calculating the recommended score of each hashtag based on the generated topical representations of multi-features. Experimental results on a real-world dataset crawled from Sina Weibo demonstrate the effectiveness of our HRMF for hashtag recommendation.

Learning to Predict Links by Integrating Structure and Interaction Information in Microblogs

Link prediction in microblogs by using unsupervised methods has been studied extensively in recent years, which aims to find an appropriate similarity measure between users in the network. However, the measures used by existing work lack a simple way to incorporate the structure of the network and the interactions between users. This leads to the gap between the predictive result and the ground truth value. For example, the F 1-measure created by the best method is around 0.2. In this work, we firstly discover the gap and prove its existence. To narrow this gap, we define the retweeting similarity to measure the interactions between users in Twitter, and propose a structural-interaction based matrix factorization model for following-link prediction. Experiments based on the real-world Twitter data show that our model outperforms state-of-the-art methods.

Location and Trajectory Identification from Microblogs

The rapid development of social networks has resulted in a proliferation of user-generated content(UGC),which can benefit many applications.In this paper,we study the problem of identifying a user's locations from microblogs,to facilitate effective location-based advertisement and recommendation.Since the location information in a microblog is incomplete,we cannot get an accurate location from a local microblog.As such,we propose a global location identification method,Glitter.Glitter combines multiple microblogs of a user and utilizes them to identify the user's locations.Glitter not only improves the quality of identifying a user's location but also supplements the location of a microblog so as to obtain an accurate location of a microblog.To facilitate location identification,Glitter organizes points of interest(POIs)into a tree structure where leaf nodes are POIs and non-leaf nodes are segments of POIs,e.g.,countries,cities,and streets.Using the tree structure,Glitter first extracts candidate locations from each microblog of a user which correspond to some tree nodes.Then Glitter aggregates these candidate locations and identifies top-κlocations of the user.Using the identified top-κuser locations,Glitter refines the candidate locations and computes top-κlocations of each microblog.To achieve high recall,we enable fuzzy matching between locations and microblogs.We propose an incremental algorithm to support dynamic updates of microblogs.We also study how to identify users'trajectories based on the extracted locations.We propose an effective algorithm to extract high-quality trajectories.Experimental results on real-world datasets show that our method achieves high quality and good performance,and scales well.

Modeling Chinese Microblogs with Five Ws for Topic Hashtags Extraction

Hashtags are important metadata in microblogs and are used to mark topics or index messages. However,statistics show that hashtags are absent from most microblogs. This poses great challenges for the retrieval and analysis of these tagless microblogs. In this paper, we summarize the similarity between microblogs and shortmessage-style news, and then propose an algorithm, named 5WTAG, for detecting microblog topics based on a model of five Ws（When, Where, Who, What, ho W）. As five-W attributes are the core components in event description, it is guaranteed theoretically that 5WTAG can properly extract semantic topics from microblogs. We introduce the detailed procedure of the algorithm in this paper including spam microblog identification, microblog segmentation, and candidate hashtag construction. In addition, we propose a novel recommendation computing method for ranking candidate hashtags, which combines syntax and semantic analysis and observes the distribution of artificial topic hashtags. Finally, we conduct comprehensive experiments to verify the semantic correctness and completeness of the candidate hashtags, as well as the accuracy of the recommendation method using real data from Sina Weibo.

Analysis of User's Weight in Microblog Network Based on User Influence and Active Degree

Based on user＇s in-degree distribution, traditional ranking algorithms of user＇s weight usually neglect the considerations of the differences among user＇s followers and the features of user＇s tweets. In order to analyze the factors which impact on user＇s weight, under the analysis of the data collected from SINA Microblog network, this paper discovers that user influence and active degrees are the dominant factors for this issue. The proposed algorithm evaluates user influence by user＇s follower number, the influence of user＇s followers and the reciprocity between users. User＇s active degree is modeled by user＇s participation and the quality of user＇s tweets. The models are tested by different data groups to confirm the parameters for the final calculation. Eventually, this paper compares the computational results with the user＇s ranking order given by the SINA official application. The performance of this algorithm presents a stronger stability on the fluctuant range of the value of user＇s weight.

Evaluation of Microblog Users’ Influence Based on PageRank and Users Behavior Analysis

This paper explores the uses’ influences on microblog. At first, according to the social network theory, we present an analysis of information transmitting network structure based on the relationship of following and followed phenomenon of microblog users. Informed by the microblog user behavior analysis, the paper also addresses a model for calculating weights of users’ influence. It proposes a U-R model, using which we can evaluate users’ influence based on PageRank algorithms and analyzes user behaviors. In the U-R model, the effect of user behaviors is explored and PageRank is applied to evaluate the importance and the influence of every user in a microblog network by repeatedly iterating their own U-R value. The users’ influences in a microblog network can be ranked by the U-R value. Finally, the validity of U-R model is proved with a real-life numerical example.

Finding the Hidden Hands:A Case Study of Detecting Organized Posters and Promoters in SINA Weibo

With the development of online social networks,a special group of online users named organized posters(or Internet water army,Internet paid posters in some literatures) have fl ooded the social network communities. They are organized in groups to post with specific purposes and sometimes even confuse or mislead normal users.In this paper,we study the individual and group characteristics of organized posters. A classifier is constructed based on the individual and group characteristics to detect them. Extensive experimental results on three real datasets demonstrate that our method based on individual and group characteristics using SVM model(IGCSVM) is effective in detecting organized posters and better than existing methods. We take a first look at finding the promoters based on the detected organized posters of our IGCSVM method. Our experiments show that it is effective in detecting promoters.

A Lightweight Sentiment Analysis Method

The emergence of big data leads to an increasing demand for data processing methods.As the most influential media for Chinese domestic movie ratings,Douban contains a huge amount of data and one can understand users'perspectives towards these movies by analyzing these data.In this article,we study movie's critics from the Douban website,perform sentiment analysis on the data obtained by crawling,and visualize the results with a word cloud.We propose a lightweight sentiment analysis method which is free from heavy training and visualize the results in a more conceivable way.

Microblog Summarization via Enriching Contextual Features Based on Sentence-Level Semantic Analysis

A novel microblog summarization approach via enriching contextual features on sentencelevel semantic analysis is proposed in this paper. At first,a Chinese sentential semantic model（ CSM） is employed to analyze the semantic structure of each microblog sentence. Then,a combination of sentence-level semantic analysis and latent dirichlet allocation is utilized to acquire extra features and related words to enrich the collection of microblog messages. The simlilarites between the two sentences are calculated based on the enriched features. Finally,the semantic weight and relation weight are calculated to select the most informative sentences,which form the final summary for microblog messages. Experimental results demonstrate the advantages of our proposed approach.The results indicate that introducing sentence-level semantic analysis for context enrichment can better represent sentential semantic. The proposed criteria,namely,semantic weight and relation weight enhance summary result. Furthermore,CSM is a useful framework for sentence-level semantic analysis.

Educational Reform in Management Courses of Agricultural & Forestry Higher Vocational Schools from the Perspective of Microblog

At present there are many socialized microblog platforms.With powerful mobility,real-time information,fragment of information dissemination,and innovation of interaction,the microblog has become a socialized interaction mode in recent years.Since microblog is very popular with students of agricultural and forestry higher vocational schools,with the rising and development of network education,the microblog as a new information platform will be used by more and more teachers in education.From the perspective of microblog,this paper studied educational reform in management courses of agricultural and forestry higher vocational schools,in the hope of providing certain reference and help for current education practice of agricultural and forestry management courses.

Study on Microblog Dissemination Law in View ol Forwarding

Forwarding is a major means of information dissemination on the Microblog platform.The article,combining static analysis and dynamic analysis,takes Microblog forwarding as the object of study,and studies the network topology of grass-roots Microblog forwarding users.It also studies the correlation between characteristic quantity and forwarding times of Microblog network topology.Furthermore,it conducts modification on virus transmission model,builds and verifies the Microblog forwarding dynamical model.The study finds out that Microblog postings present qute strong dissemination capacity on the initial stage,and some Microblog postings with many forwarding times and long duration of forwarding process due to the dynamic growth of the forwarding user network and the joining of strong nodes make network infection density decrease in some phases.

Predicting Stock Using Microblog Moods

Some research work has showed that public mood and stock market price have some relations in some degree. Although it is difficult to clear the relation, the research about the relation between stock market price and public mood is interested by some scientists. This paper tries to find the relationship between Chinese stock market and Chinese local Microblog. First, C-POMS(Chinese Profile of Mood States) was proposed to analyze sentiment of Microblog feeds. Then Granger causality test confirmed the relation between C-POMS analysis and price series. SVM and Probabilistic Neural Network were used to make prediction, and experiments show that SVM is better to predict stock market movements than Probabilistic Neural Network. Experiments also indicate that adding certain dimension of C-POMS as the input data will improve the prediction accuracy to 66.667%. Two dimensions to input data leads to the highest accuracy of 71.429%, which is about 20% higher than using only history stock data as the input data. This paper also compared the proposed method with the ROSTEA scores, and concluded that only the proposed method brings more accurate predicts.

Microblog User Recommendation Based on Particle Swarm Optimization

Considering that there exists a strong similarity between behaviors of users and intelligence of swarm of agents,in this paper we propose a novel user recommendation strategy based on particle swarm optimization(PSO)for Microblog network. Specifically,a PSO-based algorithm is developed to learn the user influence,where not only the number of followers is incorporated,but also the interactions among users(e.g.,forwarding and commenting on other users' tweets). Three social factors,the influence and the activity of the target user,together with the coherence between users,are fused to improve the performance of proposed recommendation strategy. Experimental results show that,compared to the well-known Page Rank-based algorithm,the proposed strategy performs much better in terms of precision and recall and it can effectively avoid a biased result caused by celebrity effect and zombie fans effect.

A time-aware query-focused summarization of an evolving microblogging stream via sentence extraction

With the number of social media users ramping up,microblogs are generated and shared at record levels.The high momentum and large volumes of short texts bring redundancies and noises,in which the users and analysts often find it problematic to elicit useful information of interest.In this paper,we study a query-focused summarization as a solution to address this issue and propose a novel summarization framework to generate personalized online summaries and historical summaries of arbitrary time durations.Our framework can deal with dynamic,perpetual,and large-scale microblogging streams.Specifically,we propose an online microblogging stream clustering algorithm to cluster microblogs and maintain distilled statistics called Microblog Cluster Vectors(MCV).Then we develop a ranking method to extract the most representative sentences relative to the query from the MCVs and generate a query-focused summary of arbitrary time durations.Our experiments on large-scale real microblogs demonstrate the efficiency and effectiveness of our approach.