No abstract

No abstract

The purpose of business sentiment analysis is to determine the emotions or attitudes expressed toward the company, products, services, personnel, or events. Text analysis are the simplest and most developed types of sentiment analysis so far. The text-based business sentiment analysis still has some unresolved challenges. For example, the machine learning algorithms are unable to recognize double meanings, jokes and allusions. The regional differences between language and non-native speech structures cannot be explained. To solve this problem, an undirected weighted graph is constructed for news topics. The sentences in an article are modeled as nodes, and the normalized sentence similarity is used as the link of the nodes, which can help avoid the influence of sentence length on the summary results. In the topic extraction process, the keywords are not limited to a single word, to achieve the purpose of improving the readability of the abstract. To improve the accuracy of sentiment classification, this work proposes a robust news mining-based business sentiment analysis framework, called BuSeD. It contains two main stages: (1) news collection and preprocessing, and (2) feature extraction and sentiment classification. In the first stage, the news is collected by using crawler tools. The news dataset is then preprocessed by reducing noises. In the second stage, topics in each article is extracted by using traditional topic extraction tools. And then a convolutional neural network (CNN)-based text analyzing model is designed to analyze news from sentence level. We conduct comprehensive experiments to evaluate the performance of BuSeD for sentiment classification. Compared with four classical classification algorithms, the proposed CNN-based classification model of BuSeD achieves the highest F1 scores. We also present a quantitative trading application based on sentiment analysis to validate BuSeD, which indicates that the news-based business sentiment analysis has high economic application value.

A facile approach is developed for the preparation of an oxygen reduction reaction (ORR) catalyst Co–N–GA‐1 by pyrolyzing a well‐designed precursor CoTPP/H2TPP@OGA. In the precursor, Co is preanchored into the porphyrinato cobalt CoTPP molecule by Co‐N4 core that is further protected by the metal‐free porphyrin H2TPP depending on the intermolecular π–π interaction during the self‐assembled process on the surface of lipophilic porous original graphene aerogel. The resulted Co–N–GA‐1 owns a Co elemental content up to 1.67%, which is ≈13 times than that of Co‐N‐CB‐1 originated from a CoTPP/H2TPP precursor absorbed on commercial carbon black. Meanwhile, CoN content accounts for 71.7% of the total Co‐based species in the Co–N–GA‐1, more than that of CoN‐GA‐2 (58.9%) originated from the CoTPP@OGA precursor. Consequently, Co–N–GA‐1 exhibits the most ORR performance among the present three catalysts with the more positive onset and half‐wave potentials of 0.96 and 0.88 V vs reversible hydrogen electrode, respectively, also superior to those of the commercial 20 wt% Pt/C and most of the Co‐based catalysts reported so far. Furthermore, Zn‐air battery assembled with Co–N–GA‐1 exhibits a higher peak power density of 110 mW cm−2 and excellent durability than that with Pt/C.