Rule-Based Weibo Messages Sentiment Polarity Classification towards Given Topics

Abstract

Weibo messages sentiment polarity classification towards given topics refers to that the machine automatically classifies whether the weibo message is of positive, negative, or neutral sentiment towards the given topic. The algorithm the sentiment analysis system CUCsas adopts to perform this task includes three steps: (1) whether there is an "exp" (short for "expression having evaluation meaning") in the weibo message; (2) whether there is a semantic orientation relationship between the exp and topic; (3) the sentiment polarity classification of the exp. CUCsas completes step (1) based on the sentiment lexicon and sentiment value assignment rules, completes step (2) based on the topic extraction and sentiment polarity classification rule base, and completes step (3) based on the sentiment computing rules. Taking 20 given topics and a total of 19,469 weibo messages released by SIGHAN-2015 Bake-off as the test data, the overall F value of the rule-based system CUCsas is 0.69 in the unrestricted test.

Building consumer confidence index based on social media big data

“…The most common adverbs are degree adverbs and negative words, both of which have unique grammatical significance and influence in the texts. In microblog texts, the use of degree words can increase or weaken the emotion intensity, while the modification of negative words would change the emotion polarity of emotion words (Chen, ; Zhu, ). On the basis of the “Chinese Degree Words” in the Internet of emotion dictionary, this study adapted the six categories of emotional intensity tagging into “extreme,” “high,” “medium,” “low” four categories, and assigned these four levels to corresponding weights (2, 1.75, 1.5, 0.5) (Lin & Guo, ).…”

“…This is consistent with the previous research conclusions. Many scholars have examined the influence of degree words when use microblog to analyze the analysis (Chen, ; Zhu, ). While Lai et al found that when microblog emotional index of elites and masses is being built, negative words considered alone did not significantly increase the predictive effect (Lai et al, ).…”

Gender Prediction for Chinese Social Media Data

“…This is particularly relevant in Chinese as characters in the logographic (meaning-based) Chinese writing system mean something different than characters in alphabetic systems, and with a larger number of characters there will be sparser n-grams. As a side note, there is work utilizing Weibo for word segmentation (e.g., Zhang et al, 2013) and sentiment analysis (e.g., Zhou, 2015); with our work we pave the way for future connections by exploring the impact of data filtering, preprocessing, and n-gram features on system performance.…”