A survey of Internet public opinion mining

Guo, Kai; Shi, Liang; Ye, Weilong; Li, Xiang

doi:10.1109/pic.2014.6972319

Cited by 20 publications

(13 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, there are mainly two methods to collect microblog data: web crawler and API interface. [16] By using the free and open API interface of microblog, a series of structured data such as the number of comments, replies, retweets and user information can be obtained. [17] According to the functions and structures, web crawler methods with a wide range of applications can be classified into general web crawler, focused web crawler, incremental web crawler and deep web crawler.…”

Section: Data Crawlingmentioning

confidence: 99%

“…Top 20 keywords of 8 clusters. the car, instructors, actually, not access to, get on, feel, taxi, like, in the morning, go out, find, take, bus, in the evening, get off, minutes, one car, place, on the road Cluster16 bus, public transportation, not access to, actually, minutes, go out, subway, be late, drivers, take a taxi, take, go back, miss, half an hour, taxi, want, in the morning, find, choose…”

mentioning

confidence: 99%

See 1 more Smart Citation

Topic Analysis of Microblog About “Didi Taxi” Based on K-means Algorithm

Lu¹,

Xiong²

2019

AJIST

View full text Add to dashboard Cite

In the age of information and digitization, most users publish and obtain real-time information by microblog in social networks. Through effective means, we can accurately discover, organize, and utilize the valuable information hidden behind the massive short texts of social networks. Then we can explore hot topics in microblog, which is conducive to public opinion monitoring and marketing development. In today's society, Didi Taxi has become a necessary choice for many users to travel. This paper applied K-means clustering algorithm to topic analysis of Sina microblog short text on Didi Taxi. We crawled 17226 search results of microblog relevant to the topic of Didi Taxi from April 2019 to June 2019. After a series of data cleaning and data preprocessing steps, we used TF-IDF method to represent 15054 pieces of text data after processing. Through the evaluation of silhouette coefficient, we set the dimension of text 300 and the number of clusters 34 with K-means. Next, we extracted 8 topic clusters from 34 clusters, which include the advantages and disadvantages of Didi Taxi and its development status. Finally, we discussed the results by human check in semantic perspective. Through the topic analysis of microblog, we can understand the public's attitude to Didi Taxi and provide the basis for the management of the government or company in the future.

show abstract

Section: Data Crawlingmentioning

confidence: 99%

mentioning

confidence: 99%

Topic Analysis of Microblog About “Didi Taxi” Based on K-means Algorithm

Lu¹,

Xiong²

2019

AJIST

View full text Add to dashboard Cite

show abstract

“…In particular, data obtained through a Web crawler will have to be processed to remove HTML tags and nontextual information (images and ads) [14,30,47], and text extracted from Twitter will need special care for hashtags, mentions, retweets, poorly written text, emoticons, written laughs, and words with repeated characters [46,48,49]. …”

Section: Text Preprocessingmentioning

confidence: 99%

“…Guo et al [30] define the concept of "Public Opinion Mining," compare different approaches used in each step of the OM pipeline and propose future directions for the field. In [20] the authors propose a faceted characterization of Opinion Mining composed of two main branches, namely opinion structure which deals with the relation between unstructured subjective text and structured conceptual elements, and Opinion Mining tools and techniques which are the means to achieve the OM task.…”

Section: Opinion Miningmentioning

confidence: 99%

Opinion Mining and Information Fusion: A survey

2016

View full text Add to dashboard Cite

“…But effective information cannot be efficiently obtained from mass data using ordinary analysis methods because of the large amount and high complexity of network public opinion information, but the emergence of data mining brings a new direction for analysis of network public opinion information. Network public opinion information can be analyzed and utilized through text mining (Guo et al 2014). Liu (2010) proposed a method of hot spot detection of network public opinion.…”

Section: Introductionmentioning

confidence: 99%

Text Mining and Data Information Analysis for Network Public Opinion

Hu¹

2019

Data Science Journal

View full text Add to dashboard Cite

Network public opinion information is massive and complex, and it is difficult to make effective use of manual means. In this paper, a method based on pattern matching and machine learning (PMML) was proposed to analyze the emotional tendencies of network public opinion. Firstly, the key words in public opinion were extracted, then the patterns were extracted and matched, and the emotional tendencies of words were calculated to obtain the pattern sequence vectors. Support vector machine (SVM) classifier was used to classify emotional tendencies. The Internet reviews of Meituan hotel were taken as the experimental subject. PMML method was found to have a high classification performance, with a maximum accuracy of 86.75%. It suggested the effectiveness of the proposed method. Then PMML method was used to classify the emotional tendencies of the collected reviews, and the results showed that the negative emotional tendency was greater than the positive tendency, which showed the inadequacy of Meituan hotel. The experiments in this paper provide some basis for the application of PMML in sentiment analysis of Internet public opinion.

show abstract

A survey of Internet public opinion mining

Cited by 20 publications

References 28 publications

Topic Analysis of Microblog About “Didi Taxi” Based on K-means Algorithm

Topic Analysis of Microblog About “Didi Taxi” Based on K-means Algorithm

Opinion Mining and Information Fusion: A survey

Text Mining and Data Information Analysis for Network Public Opinion

Contact Info

Product

Resources

About