• An improved OVO strategy is proposed.• A framework for multi-class sentiment classification based on the improved OVO strategy and the SVM algorithm is presented.• A new method for multi-class ...sentiment classification is proposed.• Experimental studies are conducted to verify the effectiveness of the proposed method.
Multi-class sentiment classification is a valuable research topic with extensive applications; however, studies in the field remain relatively scarce. In the present paper, a method for multi-class sentiment classification based on an improved one-vs-one (OVO) strategy and the support vector machine (SVM) algorithm is proposed. First, an improved OVO strategy is proposed wherein the relative competence weight of each binary classifier is determined according to the K nearest neighbors and the class center of each class in the training sample set concerning the binary classifier. A method for multi-class sentiment classification is proposed based on this improved OVO strategy and the SVM algorithm. After converting the training texts into term feature vectors, the important features (terms) for multi-class sentiment classification are selected using the information gain (IG) algorithm. A binary SVM classifier is then trained on the training feature vectors of each pair of sentiment classes. To identify the sentiment class of a test text, a confidence score matrix of multiple SVM classifiers is constructed based on the results of multiple SVM classifiers. Using this score matrix, the sentiment class of the test text can be determined using the improved OVO strategy. The results of our experimental studies show that the performance of the proposed method is significantly better than that of the existing methods for multi-class sentiment classification.
Pure organic materials with intrinsic room‐temperature phosphorescence typically rely on heavy atoms or heteroatoms. Two different strategies towards constructing organic room‐temperature ...phosphorescence (RTP) species based upon the through‐space charge transfer (TSCT) unit of 2.2paracyclophane (PCP) were demonstrated. Materials with bromine atoms, PCP‐BrCz and PPCP‐BrCz, exhibit RTP lifetime of around 100 ms. Modulating the PCP core with non‐halogen‐containing electron‐withdrawing units, PCP‐TNTCz and PCP‐PyCNCz, successfully elongate the RTP lifetime to 313.59 and 528.00 ms, respectively, the afterglow of which is visible for several seconds under ambient conditions. The PCP‐TNTCz and PCP‐PyCNCz enantiomers display excellent circular polarized luminescence with dissymmetry factors as high as −1.2×10−2 in toluene solutions, and decent RTP lifetime of around 300 ms for PCP‐TNTCz enantiomers in crystalline state.
A series of organic phosphors based on paracyclophanes (PCPs) exhibit both strong room‐temperature phosphorescence (RTP) and excellent circularly polarized luminescence. Modulating the PCP core with non‐halogen‐containing electron‐withdrawing units elongates the RTP lifetime to 313.59 and 528.00 ms. The afterglow is visible for several seconds under ambient conditions.
The effects of HLA-identical sibling donor (ISD) hematopoietic stem cell transplantation (HSCT) on adults with intermediate- or high-risk acute myeloid leukemia (AML) in the first complete remission ...(CR1) are well established. Previous single-center studies have demonstrated similar survival after unmanipulated haploidentical donor (HID) vs ISD HSCT for hematologic malignancies. To test the hypothesis that haploidentical HSCT would be a valid option as postremission therapy for AML patients in CR1 lacking a matched donor, we designed a disease-specific, prospective, multicenter study. Between July 2010 and November 2013, 450 patients were assigned to undergo HID (231 patients) or ISD HSCT (219 patients) according to donor availability. Among HID and ISD recipients, the 3-year disease-free survival rate was 74% and 78% (P = .34), respectively; the overall survival rate was 79% and 82% (P = .36), respectively; cumulative incidences of relapse were 15% and 15% (P = .98); and those of the nonrelapse-mortality were 13% and 8% (P = .13), respectively. In conclusion, unmanipulated haploidentical HSCT achieves outcomes similar to those of ISD HSCT for AML patients in CR1. Such transplantation was demonstrated to be a valid alternative as postremission treatment of intermediate- or high-risk AML patients in CR1 lacking an identical donor. This trial was registered at www.chictr.org as #ChiCTR-OCH-10000940.
•Haploidentical transplant achieves outcomes similar to those of identical-sibling transplant for AML patients in first remission.•Haploidentical transplant is a valid postremission treatment of intermediate- or high-risk AML patients lacking an identical donor.
This paper proposes a methodology for conducting importance-performance analysis (IPA) through online reviews. The methodology is composed of three stages: (1) mining useful information from online ...reviews, (2) estimating each attribute's performance and importance, and (3) constructing IPA plot, where the latent dirichlet allocation (LDA), the improved one-vs-one strategy based support vector machine (IOVO-SVM) and the ensemble neural network based model (ENNM) are respectively used. A case study on two five-star hotels is given, and the results obtained by the proposed methodology through online reviews are compared with those obtained by the existing methods through questionnaires (or online ratings). The results indicate that the proposed methodology can obtain effective analysis results with lower cost and shorter time since online reviews are publicly available and easily collected. The proposed methodology can give managers or market analysts one more choice for conducting IPA or serve as a preparing process of large-scale survey.
•A novel methodology for conducting IPA through online reviews is proposed.•The performance of each attribute is estimated according to the sentiment strengths of online reviews.•The importance of each attribute is estimated using ENNM.•Four types of IPA can be easily conducted through online reviews.•A case study of IPA for two five-star hotels is given.
Considerable evidence suggests that during the progression of complex diseases, the deteriorations are not necessarily smooth but are abrupt, and may cause a critical transition from one state to ...another at a tipping point. Here, we develop a model-free method to detect early-warning signals of such critical transitions, even with only a small number of samples. Specifically, we theoretically derive an index based on a dynamical network biomarker (DNB) that serves as a general early-warning signal indicating an imminent bifurcation or sudden deterioration before the critical transition occurs. Based on theoretical analyses, we show that predicting a sudden transition from small samples is achievable provided that there are a large number of measurements for each sample, e.g., high-throughput data. We employ microarray data of three diseases to demonstrate the effectiveness of our method. The relevance of DNBs with the diseases was also validated by related experimental data and functional analysis.
•A new kind of large group decision-making (LGDM) problem is formulated.•A framework for solving the LGDM problem is presented.•A technology for determining the decision weights of different ...subgroups is proposed.•An approach to ranking alternatives in LGDM analysis is presented.•A case study is used to illustrate the use of the proposed method.
Large group decision-making (LGDM) is a special group decision-making (GDM) problem, in which a large number of persons take part in decision process, while research concerning this issue is still relatively scarce. The objective of this paper is to develop a method to solve the LGDM problem, in which a large number of persons from multiple groups take part in the decision process and express their personal evaluations on the alternatives according to the pre-established identifier set. In the method, the percentage distribution on evaluations of each group concerning each alternative is determined. The decision weight of each group concerning each alternative is obtained by aggregating the subjective weight, which is provided by the organizer, and the objective weight, determined according to the level of consensus among participators' evaluations. According to the percentage distributions and decision weights, the dominance degrees on pairwise comparisons of alternatives are calculated, and a ranking of alternatives can be determined using the PROMETHEE II method. Finally, an example is given to illustrate the use of the proposed method.
Anaerobic digestion is an effective technology to treat food waste, with methane production as renewable bioenergy. However, there are two key problems in the practical application, i.e., poor system ...stability and low reactor efficiency. In this paper, additives used in anaerobic digestion of food waste were systematically reviewed in view of system stability and reactor efficiency. Enzymes showed excellent property in food waste pre-hydrolysis stage with almost all macromolecular matters being rapidly resolved. Fungi fermentation process to produce hydrolytic enzymes, can be regarded as a promising and low-cost way to realize rate-limiting step elimination. It can be also concluded that adding neutralizers, buffer chemicals and some other materials are effective to maintain the pH level for practical application. Trace metals in food waste are not enough but needed for methanogens activation in long term and high loading rate operation. In addition, direct interspecies electron transfer could be much helpful for intermediate refractory organic acids degradation and methanogenesis promotion with additives of conductive materials, which is also discussed and should be studied further in anaerobic digestion of food waste. Based on literature review, a new concept is proposed for further study, suggesting that after being well liquefied with enzyme pre-hydrolysis, food waste could be co-digested with landfill leachate in a high-rate anaerobic reactor stably, resulting in a high bioenergy recovery efficiency.
•Poor system stability and low reactor efficiency are two main problems of AD of FW.•Additives for AD of FW are reviewed regarding system stability and efficiency.•Perspectives for future study on application of economical additives are discussed.•Co-digestion of FW and landfill leachate in high rate reactors is proposed.
•A new problem on ranking products through online reviews is formulated.•A resolution process for the problem is presented.•A new algorithm is given to identify the sentiment orientations on products ...concerning features.•An approach for converting the identified sentiment orientations into intuitionistic fuzzy numbers is proposed.•An approach to ranking the products based on the intuitionistic fuzzy set theory is given.
Online product reviews have significant impacts on consumers’ purchase decisions. To support consumers’ purchase decisions, how to rank the products through online reviews is a valuable research topic, while research concerning this issue is still relatively scarce. This paper proposes a method based on the sentiment analysis technique and the intuitionistic fuzzy set theory to rank the products through online reviews. An algorithm based on sentiment dictionaries is developed to identify the positive, neutral or negative sentiment orientation on the alternative product concerning the product feature in each review. According to the identified positive, neutral and negative sentiment orientations, an intuitionistic fuzzy number is constructed for representing the performance of an alternative product concerning a product feature. The ranking of alternative products is determined by intuitionistic fuzzy weighted averaging (IFWA) operator and preference ranking organization methods for enrichment evaluations II (PROMETHEE II). A case study is given to illustrate the use of the proposed method. The comparisons and experiments are further conducted to illustrate the characteristics and advantages of the proposed method. Converting the identified positive, neutral and negative sentiment orientations into intuitionistic fuzzy numbers is a new idea for processing and fusing a large number of sentiment orientations of online reviews. Based on the proposed method, decision support system can be developed to support the consumers’ purchase decisions more conveniently.
Single-cell RNA sequencing (scRNA-seq) data provides unprecedented opportunities to reconstruct gene regulatory networks (GRNs) at fine-grained resolution. Numerous unsupervised or self-supervised ...models have been proposed to infer GRN from bulk RNA-seq data, but few of them are appropriate for scRNA-seq data under the circumstance of low signal-to-noise ratio and dropout. Fortunately, the surging of TF-DNA binding data (e.g. ChIP-seq) makes supervised GRN inference possible. We regard supervised GRN inference as a graph-based link prediction problem that expects to learn gene low-dimensional vectorized representations to predict potential regulatory interactions.
In this paper, we present GENELink to infer latent interactions between transcription factors (TFs) and target genes in GRN using graph attention network. GENELink projects the single-cell gene expression with observed TF-gene pairs to a low-dimensional space. Then, the specific gene representations are learned to serve for downstream similarity measurement or causal inference of pairwise genes by optimizing the embedding space. Compared to eight existing GRN reconstruction methods, GENELink achieves comparable or better performance on seven scRNA-seq datasets with four types of ground-truth networks. We further apply GENELink on scRNA-seq of human breast cancer metastasis and reveal regulatory heterogeneity of Notch and Wnt signalling pathways between primary tumour and lung metastasis. Moreover, the ontology enrichment results of unique lung metastasis GRN indicate that mitochondrial oxidative phosphorylation (OXPHOS) is functionally important during the seeding step of the cancer metastatic cascade, which is validated by pharmacological assays.
The code and data are available at https://github.com/zpliulab/GENELink.
Supplementary data are available at Bioinformatics online.
With the rapid advances in information technology, an increasing number of online reviews are posted daily on the Internet. Such reviews can serve as a promising data source to understand customer ...satisfaction. To this end, in this paper, we proposed a method for modelling customer satisfaction from online reviews. In the method, customer satisfaction dimensions (CSDs) are first extracted from online reviews based on latent dirichlet allocation (LDA). The sentiment orientations of the extracted CSDs are identified using a support vector machine (SVM). Then, considering the existence of complex relationships among different CSDs and the customer satisfaction, an ensemble neural network based model (ENNM) is proposed to measure the effects of customer sentiments toward different CSDs on customer satisfaction. On this basis, to identify the category of each CSD from the customer's perspective, an effect-based Kano model (EKM) is proposed. Finally, an empirical study, which consists of two parts (phones and cameras), is given to illustrate the effectiveness of the proposed method.