[Objective] This paper analyzes the mobile shoppers’ information browsing behaviors, aiming to find their influences on purchasing decisions. [Methods] We studied 44,932,715 browsing logs generated by 2,752 users of a mobile shopping APP in March, 2015. [Results] We found that users’ purchasing behaviors were affected by the complexity, breadth and depth of browsing patterns. The complexity of single-session was higher than the multi-session ones, while the complexity of multi-task process was higher than their single-task counterparts. [Limitations] More research is needed to examine data from other m-commerce platforms. [Conclusions] Mobile shoppers’ information browsing behaviors could help us better understand purchasing decisions.
[Objective] This paper tries to evaluate Web information for ancient villages based on the rank aggregation method. [Methods] First, we proposed the framework and method to evaluate Web information resources for the ancient villages. Then, we selected six dimensions of observation, and constructed the evaluation index system. Third, we aggregated several evaluation methods using the BILPS technique, as well as combining subjective and objective weights. Finally, we evaluated the ancient village’s online presence with the proposed algorithm. [Results] We examined 64 ancient villages in China’s Guangdong Province and found that most of the Top 10 ancient villages were in the provincial city of Guangzhou. [Limitations] We only investigated the web information resources for ancient villages in Guangdong Province, more research is needed to study ancient villages in other regions. [Conclusions] This study could help decision-makers, managers and local residents better understand the ancient villages’ online impacts, and then promote their development.
[Objective] This paper tries to discover the impacts of micro-blog posts, industry news and company announcements on investors’ overtrading. [Methods] We examined the variations of the abnormal stock turnover rates before and after information disclosure from different channels. [Results] Media information posed significant impacts on overtrading, including the insider effect, information disclosure effect and lasting effect before, during and after the disclosure. Besides, investors were more likely to overtrade once exposed to negative news than positive news. The limited attention, selective attention, and mood fluctuation, were correlated to the investors’ trading behaviors. [Limitations] The sample size could be expanded. Individual investors may not be aware of the findings. [Conclusions] Media information catalyzes the overtrading of irrational investors.
[Objective] This study aims to find the reasons of continuously using social commerce sites. [Methods] We developed a theoretical model for continuance intention to use social commerce sites based on the S-O-R model as well as the technology factors and perceived values. A total of 330 valid samples were collected via an online questionnaire, which were analyzed by PLS-SEM. [Results] We found that interactivity significantly affected perceived hedonic values, personalization significantly impacted perceived utilitarian values, sociability had a significant effect on perceived values, and recommendation significantly influenced perceived utilitarian and hedonic values. Meanwhile, perceived utilitarian and hedonic values significantly affected continuance intention to use social commerce sites. [Limitations] First, this study only focuses on the effects of beneficial values rather than the risks. Second, our data was collected from young users. Third, social commerce sites might lead to different browsing behaviors. [Conclusions] Technological factors and perceived values pose some effect to continuance intention to use social commerce sites. This study provides references and guidelines for related service providers.
[Objective] This study examines the impacts of user reviews on the adoption of ideas from Salesforce, an open innovation platform. [Methods] First, we divided information from Salesforce into the normative and informational categories based on the social impact theory. Then, we obtained the emotional variables of the idea’s title, content and comments with the help of text analytics to study their impacts on the idea’s implementation. [Results] The length of idea titles and contents, the title sentiment and the idea score had significant impacts on its adoption. The number of comments also influenced the comment’s sentiment. [Limitetions] We only investigated data from one platform. [Conclusions] This research helps enterprises evaluate and identify valuable ideas quickly, which also increases the probability of idea implementation.
[Objective] This paper aims to explore users’ relationship network and behaviors in the social question and answer (Q&A) communities. [Methods] First, we retrieved the publicly accessible user profiles and Q&A data from Zhihu.com, a popular online Q&A community in China. Then, we analyzed the social network structure, the user profiles and the time statistics of users’ behaviors based on complex network and human dynamics theories. [Results] The Zhihu users showed some similar behaviors at the individual and group levels. The inter-event time and waiting time followed the power-law distribution, with power index values of 0.68 and 1.51, respectively. The degree distribution of the relationship network, the amount of users’ answers, support, and comments met the exponential truncated power-law distribution. The overall behaviors of Zhihu users were of significant heterogeneity and multiple scale characteristics. [Limitations] The sample size needs to be expanded and more research is needed to compare our findings with studies of other social Q&A communities. [Conclusions] This study reveals the relationship between the user’s behaviors and information dissemination on Zhihu.com, which explores the network structure and the information flow of social question and answer communities.
[Objective] This study aims to establish a fair and objective evaluation mechanism for academic impacts, aiming to solve the issues like huge appraisal system, complicated calculation and vague conclusion. [Methods] We proposed a ranking method for each scholar’s impacts based on citation behavior and academic similarity, as well as with the help of Word2Vec, TF-IDF, and PageRank algorithms. [Results] The proposed method combined the influence of a researcher’s scholarly relationship and academic outputs. It has excellent performance in the validity dimension: the relevance of H index and the center of the feature vector with the PR value were 0.872 and 0.617, respectively. The proposed evaluation index could replace the traditional metrics. The average H-index and citation frequency of the scholars within the fixed-ranking interval both increased. The average H-index of the top 100 scholars increased by 1.087 and the average cited frequency increased by 2.080, which were better than the original PageRank algorithm. [Limitations] The efficiency of the proposed algorithm was lower than the PageRank algorithm. [Conclusions] Our new algorithm could be used to analyze academic networks with a large number of nodes. The node’s PR value will be more accurate as the network quality expands. Therefore, the new ranking algorithm could effectively evaluate the academic impacts of many scholars from multi-disciplinary fields, and has better performance than the existing ones.
[Objective] This study aims to assess and identify malicious websites with the help of multi-source evaluation metrics. [Methods] We used the principal component analysis (PCA) to conduct a multi-dimensional assessment of malicious websites based on multi-source metrics of websites. Then, we built a malicious site identification model using random forest based on the assessment. [Results] We found that the PCA could effectively extract five assessment dimensions: authority, references, website traffic, ranking, and links. Meanwhile, the identification model was accurate and efficient. [Limitations] Most of the samples in this study were foreign websites, which means the extracted dimensions may be different from those in China. Additionally, we did not study the ratio of malicious to normal websites. [Conclusions] The proposed model could effectively extract dimensions for website assessment and then identifies the malicious ones.
[Objective] This study aims to address the issues facing the topic model of patent text analysis such as the inclining to high frequency words and low discrimination rates. [Methods] First, we proposed a word weighting method for the traditional topic model. Then, the modified model assigned different weights to the words, and changed the probability of generating new words. [Results] Compared with traditional methods, the weighted patent topic model could identify the subjects more effectively. [Limitations] The weighting algorithm needs to be validated and optimized with more datasets. [Conclusions] The proposed model could effectively analyze the patent texts.
[Objective] This paper presents a novel algorithm based on the NLP technique and complex network theory, aiming to extract product features more effectively. [Methods] First, we constructed a weighted bipartite graph with the product features and sentiment words, which described their relationship more clearly and intuitively from network perspective. Then, we proposed the NodeRank algorithm to rank the importance of product features, which improved the precision of feature extraction. [Results] We examined the proposed algorithm with data from jd.com, a popular online shopping site in China. The precision, recall and F-score of the NodeRank algorithm were better than the HAC, TF-IDF and TextRank methods. [Limitations] The computational complexity of our new algorithm needs to be optimized. [Conclusions] The NodeRank algorithm could effectively extract the product features, which supports marketing and other business activities.
[Objective] This paper aims to explore the information behaviors of mobile social network (WeChat) users. [Methods] We crawled the WeChat users’ published posts in the past 5 years, and analyzed their information behaviors based on their characteristics, information contents, WeChat message posted time, WeChat Like and comment numbers. [Results] User-generated contents were affected by the user’s characteristics. There were significant differences among the numbers of Like and comments on different contents. WeChat users’ information posting intervals showed that most WeChat behaviors occurred within a short period of time. [Limitations] The sample size needs to be expanded to generalize our conclusions. [Conclusions] This study provides theoretical foundations for analyzing the behaviors of mobile social network users.