作者: Lin Zhang , Kun Hua , Honggang Wang , Guanqun Qian , Li Zhang
DOI: 10.1016/J.PROCS.2014.07.013
关键词:
摘要: Abstract In recent years, the dramatic increase of smartphone and tablet applications has allowed users to comment on various service platforms at any time through mobile internet, social media, cloud computing, etc. While unfortunately, up now, very few studies classification methods have been applied in such area. this paper, we concluded following unique characteristics more than 1,400,000 real application reviews: (1) Short average length; (2) Large span (3) Power-law distribution (4) Significant difference polarity. Based above mentioned characteristics, a series comparative experiments done for emotion classifications algorithms, feature representations review length, respectively.