共查询到20条相似文献，搜索用时 46 毫秒
1.
《Information processing & management》2019,56(3):823-843
A vast number of user opinions are available from reviews posted on e-commerce websites. Although these opinions are a valuable source of knowledge for both manufacturers and customers, they provide volumes of information that exceeds the human cognitive processing capacity, which can be a major bottleneck for their effective use. To address this problem, a number of opinion-summarization methods have been proposed to organize these opinions by grouping them around aspects. However, these methods tend to generate an excessive number of aspect groups that are frequently overly generic and difficult to interpret. We argue that a superior alternative would be to organize opinions around product attributes as defined in a product catalog. Typically, product attributes correspond to the most important characteristics of the products. Furthermore, they are common to all products in a given category and thus, form a more stable set than aspects. In this paper, we propose a novel approach called OpinionLink to products in a catalog at the attribute granularity level with opinions extracted from product reviews. The proposed approach is divided into two phases. In the first phase, OpinionLink uses a classifier to identify opinionated sentences in the reviews on a particular product. In the second phase, another classifier is used to map the opinions that were previously extracted from the user reviews to the attributes of the products in the product catalog. We performed a series of experiments on these phases. For the first phase, our experiments indicated that using classifiers with the proposed features achieved an average of 0.87 in terms of F1 measure for the task of identifying opinionated sentences. In the second phase, the method we proposed for the opinion-mapping task achieved an average of 0.85 in terms of F1. Further, we verified the effectiveness of the proposed approach as a realistic end-to-end application, indicating that we can use OpinionLink in a real setting. Finally, we empirically demonstrate the feasibility of using the proposed approach with an extremely large volume of opinions available in a collection of more than 600,000 real reviews. We also set forth a number of directions for future research. 相似文献
2.
Analyzing review sentiments and product images by parallel deep nets for personalized recommendation
《Information processing & management》2023,60(1):103166
Recommendation is an effective marketing tool widely used in the e-commerce business, and can be made based on ratings predicted from the rating data of purchased items. To improve the accuracy of rating prediction, user reviews or product images have been used separately as side information to learn the latent features of users (items). In this study, we developed a hybrid approach to analyze both user sentiments from review texts and user preferences from item images to make item recommendations more personalized for users. The hybrid model consists of two parallel modules to perform a procedure named the multiscale semantic and visual analyses (MSVA). The first module is designated to conduct semantic analysis on review documents in various aspects with word-aware and scale-aware attention mechanisms, while the second module is assigned to extract visual features with block-aware and visual-aware attention mechanisms. The MSVA model was trained, validated and tested using Amazon Product Data containing sampled reviews varying from 492,970 to 1 million records across 22 different domains. Three state-of-the-art recommendation models were used as the baselines for performance comparisons. Averagely, MSVA reduced the mean squared error (MSE) of predicted ratings by 6.00%, 3.14% and 3.25% as opposed to the three baselines. It was demonstrated that combining semantic and visual analyses enhanced MSVA's performance across a wide variety of products, and the multiscale scheme used in both the review and visual modules of MSVA made significant contributions to the rating prediction. 相似文献
3.
《Information processing & management》2020,57(6):102304
The way that users provide feedback on items regarding their satisfaction varies among systems: in some systems, only explicit ratings can be entered; in other systems textual reviews are accepted; and in some systems, both feedback types are accommodated. Recommender systems can readily exploit explicit ratings in the rating prediction and recommendation formulation process, however textual reviews -which in the context of many social networks are in abundance and significantly outnumber numeric ratings- need to be converted to numeric ratings. While numerous approaches exist that calculate a user's rating based on the respective textual review, all such approaches may introduce errors, in the sense that the process of rating calculation based on textual reviews involves an uncertainty level, due to the characteristics of the human language, and therefore the calculated ratings may not accurately reflect the actual ratings that the corresponding user would enter. In this work (1) we examine the features of textual reviews, which affect the reliability of the review-to-rating conversion procedure, (2) we compute a confidence level for each rating, which reflects the uncertainty level for each conversion process, (3) we exploit this metric both in the users’ similarity computation and in the prediction formulation phases in recommender systems, by presenting a novel rating prediction algorithm and (4) we validate the accuracy of the presented algorithm in terms of (i) rating prediction accuracy, using widely-used recommender systems datasets and (ii) recommendations generated for social network user satisfaction and precision, where textual reviews are abundant. 相似文献
4.
《Information processing & management》2022,59(2):102842
The matrix factorization model based on user-item rating data has been widely studied and applied in recommender systems. However, data sparsity, the cold-start problem, and poor explainability have restricted its performance. Textual reviews usually contain rich information about items’ features and users’ sentiments and preferences, which can solve the problem of insufficient information from only user ratings. However, most recommendation algorithms that take sentiment analysis of review texts into account are either fine- or coarse-grained, but not both, leading to uncertain accuracy and comprehensiveness regarding user preference. This study proposes a deep learning recommendation model (i.e., DeepCGSR) that integrates textual review sentiments and the rating matrix. DeepCGSR uses the review sets of users and items as a corpus to perform cross-grained sentiment analysis by combining fine- and coarse-grained levels to extract sentiment feature vectors for users and items. Deep learning technology is used to map between the extracted feature vector and latent factor through the rating-based matrix factorization model and obtain deep, nonlinear features to predict the user's rating of an item. Iterative experiments on e-commerce datasets from Amazon show that DeepCGSR consistently outperforms the recommendation models LFM, SVD++, DeepCoNN, TOPICMF, and NARRE. Overall, comparing with other recommendation models, the DeepCGSR model demonstrated improved evaluation results by 14.113% over LFM, 13.786% over SVD++, 9.920% over TOPICMF, 5.122% over DeepCoNN, and 2.765% over NARRE. Meanwhile, the DeepCGSR has great potential in fixing the overfitting and cold-start problems. Built upon previous studies and findings, the DeepCGSR is the state of the art, moving the design and development of the recommendation algorithms forward with improved recommendation accuracy. 相似文献
5.
《Information processing & management》2020,57(2):102031
Social media platforms allow users to express their opinions towards various topics online. Oftentimes, users’ opinions are not static, but might be changed over time due to the influences from their neighbors in social networks or updated based on arguments encountered that undermine their beliefs. In this paper, we propose to use a Recurrent Neural Network (RNN) to model each user’s posting behaviors on Twitter and incorporate their neighbors’ topic-associated context as attention signals using an attention mechanism for user-level stance prediction. Moreover, our proposed model operates in an online setting in that its parameters are continuously updated with the Twitter stream data and can be used to predict user’s topic-dependent stance. Detailed evaluation on two Twitter datasets, related to Brexit and US General Election, justifies the superior performance of our neural opinion dynamics model over both static and dynamic alternatives for user-level stance prediction. 相似文献
6.
[目的/意义] 在线医评信息对构建互联网医疗信任十分重要,但目前医评网站中医生人均评论十分有限。因此,探索用户生成在线医评信息的影响因素有利于促进互联网医疗的发展。[方法/过程] 对34位健康信息用户进行半结构化访谈,基于扎根理论对资料进行开放性编码、主轴编码和选择性编码。[结果/结论] 通过分析得到45个初始概念、15个范畴及对应的用户认知、用户个体特征、医疗环境和医生特征4个主范畴,在此基础上构建了用户生成在线医评信息的影响因素模型,并从医疗政策、医疗服务提供者、网络医疗平台和网络用户4个方面提出相应的激励对策。研究结果对在线医评信息生成的影响因素提供了理论支持,对促进在线医评信息的生成提供了对策和思路。 相似文献
7.
《International Journal of Information Management》2016,36(3):397-402
Online video recommender systems help users find videos suitable for their preferences. However, they have difficulty in identifying dynamic user preferences. In this study, we propose a new recommendation procedure using changes of users’ facial expressions captured every moment. Facial expressions portray the users’ actual emotions about videos. We can utilize them to discover dynamic user preferences. Further, because the proposed procedure does not rely on historical rating or purchase records, it properly addresses the new user problem, that is, the difficulty in recommending products to users whose past rating or purchase records are not available. To validate the recommendation procedure, we conducted experiments with footwear commercial videos. Experiment results show that the proposed procedure outperforms benchmark systems including a random recommendation, an average rating approach, and a typical collaborative filtering approach for recommendation to both new and existing users. From the results, we conclude that facial expressions are a viable element in recommendation. 相似文献
8.
Customers commonly share opinions and experiences about products via the internet by means of social media and networking sites. The generated textual data is often analysed by means of Sentiment Analysis (SA) as means to assess customer opinions on product features more efficiently than through surveys. To enable a more objective product target setting, the impact of product feature performance changes on customer satisfaction is essential. Kano et al. (1984) presented a survey-based model to classify product features based on their impact on customer satisfaction to aid designers in their product target setting. Approaches extending the Kano model rely on customer surveys as input data. In addition, existing studies classifying extracted product features from textual data (e.g. product reviews) rarely provide a clear separation in terms of Kano categories. Thus, the impact of identified product features on customer satisfaction remains unknown to product designers. This paper presents a methodology for autonomously classifying extracted aspects from textual data into Kano categories. For verification purposes, two examples using coffee machine and smartphone user reviews are presented. Results indicate that the proposed methodology efficiently provides product designers with insightful customer information through the proposed aspect categorization. 相似文献
9.
【目的/意义】目前,越来越多的消费者参与在线评论进行信息交互和需求表达。从丰富的在线产品评论中
识别并分析用户需求有助于企业有针对性地提升产品及服务质量,从而推动企业可持续发展。【方法/过程】本文利
用LDA模型对在线手机评论进行评论主题及产品特征挖掘,有效识别用户需求要素。基于Kano模型设置用户需
求调查问卷,结合用户满意指数分析各项需求对用户满意度的影响,确定各类用户需求重要度和供给优先级顺
序。【结果/结论】本文将24项用户需求要素划分为6项高魅力型需求、8项低魅力型需求、3项高期望型需求、3项高
必备型需求、2项低必备型需求、2项无差异型需求,进一步提出企业产品管理的优化策略。【创新/局限】本文利用文
本挖掘方法对真实的在线评论进行用户需求分析,有效克服传统用户需求调查方法中存在的需求来源滞后及可靠
性不足等问题。此外,本文所选产品的品牌相同,后续研究可向多平台及多品牌的产品需求分析进行改进和深化。 相似文献
10.
Consumers’ software purchase decisions are influenced both by online reviews and by their experiences with free samples provided by firms. This paper empirically investigates the differential effects of online reviews (user and editor ratings) on consumers’ sample downloading behavior, using a dataset drawn from a large software free sampling website CNET.com. Our findings extend the previous research by suggesting that information disclosure levels of free samples (indicated by licenses) moderates the impacts of online reviews on consumers’ sample downloads. For samples that disclose a great level of information, higher user ratings can increase downloads; otherwise, higher user ratings fail to increase downloads. When both user and editor ratings are available to consumers, only user ratings can increase sample downloads. The findings can be explained by consumers’ two-stage information process whereby consumers first refer to online reviews and then determine whether to sample software. This study provides practical implications on the design of information disclosure channel and offers suggestions for firms regarding how to select and apply sample licenses. 相似文献
11.
Web2.0时代,阅读在线产品评论已经成为人们购物前的一种习惯。然而,网络上的评论数量巨大且观点不一,消费者很难获取到真正对其有用的评论。本文从研究中文在线产品评论的有用性评估入手,结合中文在线评论的特点,构建了评论有用性评估特征体系。以二分类思想为中心,基于文本挖掘的基本流程,实现对中文产品评论的分类,并考察了评论内容各特征对分类效果的影响。结果表明,本文提出的评估方法能有效识别出有用评论,并且发现浅层句法特征在分类中的贡献度较高,语义特征与情感特征则会因语料类型的不同而有不同的分类贡献度。 相似文献
12.
Ding Xiao Yugang Ji Yitong Li Fuzhen Zhuang Chuan Shi 《Information processing & management》2018,54(6):861-873
Aspect mining, which aims to extract ad hoc aspects from online reviews and predict rating or opinion on each aspect, can satisfy the personalized needs for evaluation of specific aspect on product quality. Recently, with the increase of related research, how to effectively integrate rating and review information has become the key issue for addressing this problem. Considering that matrix factorization is an effective tool for rating prediction and topic modeling is widely used for review processing, it is a natural idea to combine matrix factorization and topic modeling for aspect mining (or called aspect rating prediction). However, this idea faces several challenges on how to address suitable sharing factors, scale mismatch, and dependency relation of rating and review information. In this paper, we propose a novel model to effectively integrate Matrix factorization and Topic modeling for Aspect rating prediction (MaToAsp). To overcome the above challenges and ensure the performance, MaToAsp employs items as the sharing factors to combine matrix factorization and topic modeling, and introduces an interpretive preference probability to eliminate scale mismatch. In the hybrid model, we establish a dependency relation from ratings to sentiment terms in phrases. The experiments on two real datasets including Chinese Dianping and English Tripadvisor prove that MaToAsp not only obtains reasonable aspect identification but also achieves the best aspect rating prediction performance, compared to recent representative baselines. 相似文献
13.
《Information processing & management》2022,59(5):103031
Online recommender systems have been shown to be vulnerable to group shilling attacks in which attackers of a shilling group collaboratively inject fake profiles with the aim of increasing or decreasing the frequency that particular items are recommended. Existing detection methods mainly use the frequent itemset (dense subgraph) mining or clustering method to generate candidate groups and then utilize the hand-crafted features to identify shilling groups. However, such two-stage detection methods have two limitations. On the one hand, due to the sensitivity of support threshold or clustering parameters setting, it is difficult to guarantee the quality of candidate groups generated. On the other hand, they all rely on manual feature engineering to extract detection features, which is costly and time-consuming. To address these two limitations, we present a shilling group detection method based on graph convolutional network. First, we model the given dataset as a graph by treating users as nodes and co-rating relations between users as edges. By assigning edge weights and filtering normal user relations, we obtain the suspicious user relation graph. Second, we use principal component analysis to refine the rating features of users and obtain the user feature matrix. Third, we design a three-layer graph convolutional network model with a neighbor filtering mechanism and perform user classification by combining both structure and rating features of users. Finally, we detect shilling groups through identifying target items rated by the attackers according to the user classification results. Extensive experiments show that the classification accuracy and detection performance (F1-measure) of the proposed method can reach 98.92% and 99.92% on the Netflix dataset and 93.18% and 92.41% on the Amazon dataset. 相似文献
14.
为促进检验检测业服务质量提升，以检验检测（IT）服务质量评级和用户服务需求为切入点，采用基于长短期记忆网络（LSTM）的深度学习方法，设计由有形性、可靠性、响应性、安全性和移情性5个维度构成的评价体系，通过检验检测-服务质量-长短期记忆网络-情感分析模型（IT-QoS-LSTM-SA）对检验检测服务机构服务质量（QoS）进行评价与反馈，并利用7万多条相关文本数据进行实证。结果显示：LSTM模型在检验检测用户评论分类中的准确率达到了85.24%；根据情感分析（SA）计算得出检验检测服务质量的总评分为0.491 6，处于满意和非常满意程度之间。由此可以直观地看出检验检测服务质量在各项评价指标上的优劣程度。 相似文献
15.
该文通过爬虫代码搜集了当前B站电影栏目列表中的所有电影(约1000部),同时爬取每部电影下的所有评分数据(约65万条),每条评分数据包含评分时间与用户的ID信息。通过非参数统计中的Mann-Whitney秩和检验对搜集的数据进行分析和研究,结果表明:B站电影栏目中第一次评分人员的比例会对评分产生显著影响。同时参考美国IMDb贝叶斯加权统计算法中只收录“老用户”评分的处理方式,对B站评分系统提出建议,使评分能更加客观、全面地为观众提供参考。 相似文献
16.
Understanding user experience (UX) becomes more important in a market-driven design paradigm because it helps designers uncover significant factors, such as user’s preference, usage context, product features, as well as their interrelations. Conventional means, such as questionnaire, survey and self-report with predefined questions and prompts, are used to collect information about users’ experience during various UX studies. However, such data is often limited and restricted by initial setups, and they won’t easily allow designers to identify all critical elements such as user profile, context, related product features, etc. Meanwhile, with widely accessible social media, the volume and velocity of customer-generated data are fast-increasing. While it is generally acknowledged that such data contains important elements in understanding and analyzing UX, extracting them to assist product design remains a challenging issue. In this study, how UX data underlying product design can be isolated and restored from customer online reviews is examined. A faceted conceptual model is proposed to elucidate the crucial factors of UX, which serves as an operational mechanism connecting to product design. A methodology of establishing a UX knowledge base from customer online reviews is then proposed to support UX-centered design activities, which consists of three stages, i.e., UX discovery to extract UX data from a single review, UX data integration to group similar data and UX network formalization to build up the causal dependencies among UX groups. Using a case study on smart mobile phone reviews, examples of UX data discovered are demonstrated and both customers and designers concerned key product features and usage situations are exemplified. This study explores the feasibility to discover valuable UX data as well as their relations automatically for product design and business strategic plan by analyzing a large volume of customer online data. 相似文献
17.
电子商务中在线评论有用投票数影响因素研究 总被引：1，自引：0，他引：1
在线评论对消费者购物选择具有重要的影响,但日益增加的海量信息导致了信息过载等问题。因此,判断和识别评论信息的有用性具有重要的研究意义。本文采用文本挖掘和统计分析方法,从评论信息特征和评论者信息两个角度,对在线评论获得有用投票数的影响因素进行了分析,并通过亚马逊商城的用户评论样本,具体研究了各因素的影响作用。研究发现：评论评分对在线评论的有用投票数具有负向影响,而评论信息丰富性和历史评论有用性评价对其具有正向影响。 相似文献
18.
[目的/意义] 在线医评信息作为健康信息的一种,在"互联网+医疗健康"时代,对健康消费者、医疗服务提供者和在线医评网站均有重要影响。[方法/过程] 通过系统检索国外在线医评信息领域的研究,围绕已发表文献的计量分析、在线医评信息的内容分析、在线医评信息特征的相关因素、用户和医生对在线医评信息的认知和利用、在线医评信息与医疗服务质量关系等5个方面,对目前在线医评信息的研究成果进行梳理和评述。[结果/结论] 在线医评信息研究得到国外不同领域学者的重视,用户生成的在线医评信息逐渐增多,与在线医评信息特征相关的因素有待进一步检验,健康消费者及医生对医评信息的认知和利用程度不断提高,在线医评信息与医疗服务质量的关系尚未得到一致结论。最后,针对现有研究的不足提出未来展望,以期对在线医评信息开展更深入地研究。 相似文献
19.
《International Journal of Information Management》2016,36(4):520-530
The research on users as a source of innovation has been coming into blossom and the studies about the effect of users’ lead userness on their innovation-related activities are drawing more and more attention from both academic and business circles. However, there have been few empirical studies exploring the relationship between users’ lead userness and their innovation-related knowledge sharing behavior in the context of online user community and the mediating effects of users’ social capital and their perceived behavioral control on this relationship. By empirically analyzing the 140 data collected from an online user community that is used as an important source of innovation for a company with the structural equation modeling analysis through the partial least squares method, this study reveals that users’ lead userness has a positive relationship with their innovation-related knowledge sharing in the online user community and users’ social capital and perceived behavioral control jointly and fully mediate this positive relationship. Based on the new findings, this study is expected to provide useful implications which can contribute to widening and deepening the research stream about the effect of users’ lead userness on their innovation-related knowledge sharing in the online user community. 相似文献
20.
《Information processing & management》2016,52(6):1200-1226
Search log analysis has become a common practice to gain insights into user search behaviour: it helps gain an understanding of user needs and preferences, as well as an insight into how well a system supports such needs. Currently, log analysis is typically focused on low-level user actions, i.e. logged events such as issued queries and clicked results, and often only a selection of such events are logged and analysed. However, types of logged events may differ widely from interface to interface, making comparison between systems difficult. Further, the interpretation of the meaning of and subsequent analysis of a selection of events may lead to conclusions out of context— e.g. the statistics of observed query reformulations may be influenced by the existence of a relevance feedback component. Alternatively, in lab studies user activities can be analysed at a higher level, such as search tactics and strategies, abstracted away from detailed interface implementation. Unfortunately, until now the required manual codings that map logged events to higher-level interpretations have prevented large-scale use of this type of analysis. In this paper, we propose a new method for analysing search logs by (semi-)automatically identifying user search tactics from logged events, allowing large-scale analysis that is comparable across search systems. In addition, as the resulting analysis is at a tactical level we reduce potential issues surrounding the need for interpretation of low-level user actions for log analysis. We validate the efficiency and effectiveness of the proposed tactic identification method using logs of two reference search systems of different natures: a product search system and a video search system. With the identified tactics, we perform a series of novel log analyses in terms of entropy rate of user search tactic sequences, demonstrating how this type of analysis allows comparisons of user search behaviours across systems of different nature and design. This analysis provides insights not achievable with traditional log analysis. 相似文献