Detecting fake reviews can help customers make better purchasing decisions and maintain a positive online business environment. In recent years, pre-trained language models have significantly improved the performance of natural language processing tasks. These models are able to generate different representation vectors for each word in different contexts, thus solving the challenge of multiple meanings of a word, which traditional word vector methods such as Word2Vec cannot solve, and, therefore, better capturing the text’s contextual information. In addition, we consider that reviews generally contain rich opinion and sentiment expressions, while most pre-trained language models, including BERT, lack the consideration of sentiment knowledge in the pre-training stage. Based on the above considerations, we propose a new fake review detection model based on a pre-trained language model and convolutional neural network, which is called BSTC. BSTC considers BERT, SKEP, and TextCNN, where SKEP is a pre-trained language model based on sentiment knowledge enhancement. We conducted a series of experiments on three gold-standard datasets, and the findings illustrate that BSTC outperforms state-of-the-art methods in detecting fake reviews. It achieved the highest accuracy on all three gold-standard datasets—Hotel, Restaurant, and Doctor—with 93.44%, 91.25%, and 92.86%, respectively.

Pancreatic cancer is an aggressive disease with dismal prognosis. It is of paramount importance to understand the underlying etiological mechanisms and identify novel, consistent, and easy-to-apply prognostic factors for precision therapy. TUSC3 (tumor suppressor candidate 3) was identified as a potential tumor suppressor gene and previous study showed TUSC3 is decreased in pancreatic cancer at mRNA level, but its putative tumor suppressor function remains to be verified. In this study, TUSC3 expression was found to be suppressed both at mRNA and protein levels in cell line models as well as in clinical samples; decreased TUSC3 expression was associated with higher pathological TNM staging and poorer outcome. In three pairs of cell lines with different NF-κB activity, TUSC3 expression was found to be reversely correlated with NF-κB activity. TUSC3-silenced pancreatic cancer cell line exhibited enhanced potential of proliferation, migration and invasion. In an orthotopic implanted mice model, TUSC3 silenced cells exhibited more aggressive phenotype with more liver metastasis. In conclusion, the current study shows that decreased immunological TUSC3 staining is a factor prognostic of poor survival in pancreatic cancer patients and decreased TUSC3 promotes pancreatic cancer cell proliferation, invasion and metastasis. The reverse correlation between NF-κB activity and TUSC3 expression may suggest a novel regulation pattern for this molecule.

The research of social influence is an important topic in online social network analysis. Influence maximization is the problem of finding $k$ nodes that maximize the influence spread in a specific social network. Robust influence maximization is a novel topic that focuses on the uncertainty factors among the influence propagation models and algorithms. It aims to find a seed set with a definite size that has robust performance with different influence functions under various uncertainty factors. In this paper, we propose a centrality-based edge activation probability evaluation method in the independent cascade model. We consider four different types of centrality measurement methods and add a modification coefficient to evaluate the edge probability. We also propose two algorithms, called NewDiscount and GreedyCIC, by incorporating the edge probability space into previous algorithms. With extensive experiments on various real online social network data sets, we find that our PageRank-based greedy algorithm has the best influence spreads and lowest running times, compared with other algorithms, on some large data sets. The experiment for evaluating the robustness performance shows that all algorithms have optimal robustness performance when the modification coefficient is set to 0.01 under the independent cascade model. This result suggests some further research directions under this model.

Community detection algorithms are important for determining the character statistics of complex networks. Compared with the conventional community detection algorithms, which always focus on undirected networks, our algorithm is concentrated on directed networks such as the WeChat moments relationship network and the Sina Micro-Blog follower relationship network. To address disadvantages such as lower execution efficiency and higher deviation of precision that current directed community detection algorithms always have, we propose a new approach that is based on the triangle structure of community basis and modeled on the local information transfer process to precisely detect communities in directed networks. Based on the directed vector theory in probability graphs and the dynamic information transfer gain (ITG) of vertices in directed networks, we propose the novel ITG method and the corresponding target optimal function for evaluating the partition quality in a community detection algorithm. Then, we combine ITG and the target function to create the new community detection algorithm ITG-directed weighted community clustering for directed networks. With extensive experiments using artificial network data sets and large, real-world network data sets derived from online social media, our algorithm proved to be more accurate and faster in directed networks than several traditional, well-known community detection methods, such as FastGN, order statistics local optimization method, and Infomap.