Recently, Twitter has received much attention, both from the general public and researchers, as a new method of transmitting information. Among others, the number of retweets (RTs) and user types are the two important items of analysis for understanding the transmission of information on Twitter. To analyze this point, we applied text classification and feature extraction experiments using random forests machine learning with conventional stylistic and Twitter-specific features. We first collected tweets from 40 accounts with a high number of followers and created tweet texts from 28,756 tweets. We then conducted 15 types of classification experiments using a variety of combinations of features such as function words, speech terms, Twitter's descriptive grammar, and information roles. We deliberately observed the effects of features for classification performance. The results indicated that class classification per user indicated the best performance. Furthermore, we observed that certain features had a greater impact on classification. In the case of the experiments that assessed the level of RT quantity, information roles had an impact. In the case of user experiments, important features, such as the honorific postpositional particle and auxiliary verbs, such as "desu" and "masu," had an impact. This research clarifies the features that are useful for categorizing tweets according to the number of RTs and user types.

No abstract

Gathering information from social media content is becoming increasingly popular. Twitter, a microblog where posts are limited to 140 characters, is an excellent platform for gathering instant and interactive information.Considerable research has focused on Twitter's effectiveness for disseminating emergency alerts and confirming the safety of acquaintances.However, there has been less emphasis on the analysis of Twitter posts to obtain information specialized to specific domains. Such analysis could enable simple and rapid identification of information related to state-of-the-art technology. Against this background, this study reports on a preliminary analysis of tweets by Japanese academic researchers. Our content analysis and text analysis reveal that many academic researchers tweet about their individual activities, education, or research. Their tweets contain domain-specific knowledge and have identifiable textual characteristics. This study provides basic findings that can be applied to obtain domain-specific knowledge from Twitter.

We have performed a pulse-shape analysis of signals from Si detectors to identify low-energy charged particles with neural networks (NNs). We acquired pulse shapes of proton, deuteron, triton, 3 He and 4 He from a CH2 target bombarded by α particles. We trained the NNs using the pulse shapes for known particles and evaluated their particle-identification ability of the NNs. The NNs successfully distinguished helium isotopes from hydrogen isotopes, but could not separate the helium isotopes into 4 He and 3 He.