改进模糊划分聚类的协同过滤推荐算法

针对传统协同过滤（CF）推荐算法存在评分矩阵稀疏、扩展性弱和推荐准确率低的缺陷，提出一种改进模糊划分聚类的协同过滤推荐算法（GIFP-CCF+）。在传统基于修正余弦相似度计算方法上，引入时间差因子、热门物品权重因子以及冷门物品权重因子以改善相似度计算结果；同时引入改进模糊划分的GIFP-FCM算法，将属性特征相似的项目聚成一类，构造索引矩阵，同索引间根据项目间的相似度寻找项目最近邻居构成推荐，从而提高协同过滤算法（CF）的精度。通过与Kmeans-CF、FCM-CF和GIFP-CCF算法进行仿真对比实验，证明了GIFP-CCF+算法在推荐结果和推荐精度上具有一定的优越性。     

融合评分与评论的深度评分预测模型

近年来，基于评论推荐模型的出现有效缓解了传统推荐算法存在的数据稀疏性问题.该类模型主要利用文本中丰富的语义信息更好地捕捉用户的偏好特征以及物品的属性特征，以补充更多的相关信息，提高推荐性能.文本特征的提取往往存在语义信息提取不精准的问题，导致推荐效果不理想.本文提出了融合评分与评论的深度评分预测模型(Deep Model combining Rating and Review, DMRR).一方面，该模型融合了评分数据与评论信息，利用评分矩阵引入物品可推荐度与用户偏好程度，使评论文本特征得到增强.另一方面，该模型有效结合了CNN与GRU进行文本信息特征提取，考虑了文本之间密切的依赖关系，以克服传统文本特征提取方法忽略上下文关系的不足.在Amazon上的4个子数据集和Yelp数据集的实验结果表明，该方法与已有的相关算法相比较，均有效地提高了评分预测准确性.     

电影推荐系统中基于图的协同过滤算法

在视频服务领域,通常使用传统的协同过滤算法来解决评分数据较为稀疏的问题,而算法的视频相似度计算仅利用评分矩阵,从而造成推荐准确度较低,针对视频资源中的电影这一应用场景提出一种基于图的协同过滤算法。结合电影属性与用户偏好的关联性,将电影信息中类型、导演和演员等信息进行图元素的映射,融合图结构特点来计算影片资源的相似度。用该方法替代传统协同过滤算法中仅利用评分矩阵的相似度计算方法,在一定程度上缓解了由于数据稀疏性影响推荐准确度的问题,实验验证了该方法的有效性。     

基于融合GMM聚类与FOA-GRNN模型的推荐算法

针对传统基于物品的推荐算法由于数据稀疏性导致的低推荐精度问题,提出了一种融合GMM聚类和FOA-GRNN模型的推荐算法。该算法首先使用高斯混合模型（GMM）方法对物品特征进行聚类;然后根据聚类结果分别构造评分矩阵,并使用Slope One算法填充评分矩阵;最后计算用户对物品的相似度预测评分作为输入,通过FOA-GRNN模型输出最终的评分。基于movielens-2k数据集的实验结果表明,与其他3种算法相比,该算法能够更好地处理高稀疏性数据,推荐精度更优,并能够在一定程度上解决冷启动问题。     

融合用户自然最近邻的协同过滤推荐算法

现有的基于近邻的协同过滤推荐方法如基于KNN、基于K-means的协同过滤推荐常用来预测用户评分,但该方法确定邻居个数K非常困难且推荐准确率不高,难以达到理想推荐效果。从选择邻居用户这一角度出发,提出一种融合用户自然最近邻的协同过滤推荐算法（Collaborative Filtering recommendation integrating user-centric Natural Nearest Neighbor,CF3N）,该算法首先自适应地寻找目标用户的自然最近邻居集,再融合目标用户的自然最近邻居集与活动近邻用户集,使用融合后得到的邻居集合预测目标用户评分。实验使用了MovieLens数据集,以RMSE和MAE为评测标准,比较CF3N、CF-KNN与INS-CF算法,结果显示在电影领域该算法的推荐准确率有显著提高。     

融合时间隐语义填充和子群划分的推荐算法

随着个性化推荐技术的发展，推荐系统面临着越来越多的挑战。传统的推荐算法通常存在数据稀疏性和推荐精度低等问题。针对以上问题，提出了一种融合时间隐语义填充和子群划分的推荐算法[K]-TLFM（Time Based Latent Factor Model Integrated with [k]-means）。该算法利用融合时间因素的隐语义模型对原始用户物品评分矩阵缺失项进行填充，避免了用全局平均值或者用户/物品平均值补全矩阵带来的误差，有效缓解了数据稀疏性问题，同时融合时间因素有效地刻画了用户偏好随时间的变化；完成评分矩阵缺失项填充后，基于二分[k]-means聚类算法将偏好、兴趣特征相似的对象划分到同一个子群中，在目标用户所属的子群中基于选定的协同过滤算法为用户产生推荐列表，提高了推荐效率和准确性。在MovieLens和Netflix数据集上对该算法的推荐性能进行了对比实验，结果表明该算法具有更高的推荐精度。     

基于情感分析的个性化推荐算法研究

对基于情感分析的个性化推荐算法进行研究。为了推荐用户可能感兴趣的产品，该算法研究了以前的评级数据和用户文本评论中的情感数据，并将其与推荐算法相结合。使用情感词典和情感分类算法对文本评论进行聚类分析，并将情感得分作为评分数据的补充，然后使用基于邻域的协同过滤算法来为用户推荐物品。使用京东评论数据集进行了实验，并与其他基于协同过滤算法进行了比较。实验结果表明，该算法能够显著提高推荐准确度和用户满意度。     

基于情感分析和LDA主题模型的协同过滤推荐算法

协同过滤推荐算法通常基于物品或用户的相似度来实现个性化推荐,但是数据的稀疏性往往导致推荐精度不理想。大多数传统推荐算法仅考虑用户对物品的总体评分,而忽略了评论文本中用户对物品各个属性面的偏好。该文提出一种基于情感分析的推荐算法SACF(reviews sentiment analysis for collaborative filtering),该算法在经典的协同过滤推荐算法的基础上,考虑评论文本对相似度计算的影响。SACF算法利用LDA主题模型挖掘物品潜在的K个属性面,通过用户在各个属性面上的情感偏好计算用户相似度,从而构建推荐模型。基于京东网上评论数据集的实验结果表明,SACF算法不但可以有效地改善传统协同过滤推荐算法中数据稀疏性的问题,而且提高了推荐系统的精度。     

基于简介和评论的标签推荐方法研究

Web 2.0时代,社会标签是信息资源组织的一种重要方式。标签推荐能够有效的帮助用户收集、定位、查找和共享在线资源。以往的标签推荐算法只是基于一种文本信息,比如基于电影的简介文本来进行标签推荐。但是实际上电影往往存在多种文本信息,比如同时存在摘要信息和评论信息,不同类型的信息能够反映电影的不同方面的属性,因此为了提高电影标签推荐的准确率和有效性,我们同时根据电影的简介和短评进行电影标签自动推荐,并使用多种方法融合基于不同类型文本的标签推荐的结果,实验证明,使用不同类型信息进行标签推荐能够比单一使用一种文本信息进行标签推荐有很大的提升。
     

基于评分偏好和项目属性的协同过滤算法

针对传统的协同过滤推荐由于数据稀疏性导致物品间相似性计算不准确、推荐准确度不高的问题,文中提出了一种基于用户评分偏好模型、融合时间因素和物品属性的协同过滤算法,通过改进物品相似度度量公式来提高推荐的准确度。首先考虑到不同用户的评分习惯存在差异这一客观现象,引入评分偏好模型,通过模型计算出用户对评分类别的偏好,以用户对评分类别的偏好来代替用户对物品的评分,重建用户-物品评分矩阵;其次基于时间效应,引入时间权重因子,将时间因素纳入评分相似度计算中;然后结合物品的属性,将物品属性相似度和评分相似度进行加权,完成物品最终相似度的计算;最后通过用户偏好公式来计算用户对候选物品的偏好,依据偏好对用户进行top-N推荐。在MovieLens-100K和MovieLens-Latest-Small数据集上进行了充分实验。结果表明,相比已有的经典的协同过滤算法,所提算法的准确率和召回率在MovieLens-100K数据集上提高了9%~27%,在MovieLens-Latest-Small数据集上提高了16%~28%。因此,改进的协同过滤算法能有效提高推荐的准确度,有效缓解数据稀疏性问题。     

Bayesian belief network for box-office performance: A case study on Korean movies

Due to their definition as experience goods with short product lifetime cycles, it is difficult to forecast the demand for motion pictures. Nevertheless, producers and distributors of new movies need to forecast box-office results in an attempt to reduce the uncertainty in the motion picture business. Previous research demonstrated the ability of certain movie attributes such as early box-office data and release season to forecast box-office revenues. However, no previous research has focused on the causal relationship among various movie attributes, which have the potential to increase the accuracy of box-office predictions. In this paper a Bayesian belief network (BBN), which is known as a causal belief network, is constructed to investigate the causal relationship among various movie attributes in the performance prediction of box-office success. Subsequently, sensitivity analysis is conducted to determine those attributes most critically related to box-office performance. Finally, the probability of a movie’s box-office success is computed using the BBN model based on the domain knowledge from the value chain of theoretical motion pictures. The results confirm the improved forecasting accuracy of the BBN model compared to artificial neural network and decision tree.     

基于VSTO的文档审阅批注自动导出技术

针对软件测试活动中文档审查后文档问题入库工作繁琐的问题,提出一种Word审阅批注自动导出方法。该方法基于VSTO进行Word功能扩展,实现自定义的批注自动化导出,提出的批注筛选定位算法实现了批注的分类识别,导出批注的同时为其自动生成定位描述。文档审阅批注以审阅报告的形式导出,通过规范导出的内容要素及描述格式,生成的批注描述可供测试人员在文档问题入库时直接粘贴复制,简化了文档问题的入库过程。     

SentiVerb system: classification of social media text using sentiment analysis

This article proposes novel frameworks of SentiVerb and Spell Checker system, which extracts the reaction, mood, and opinion of users from social media text (SMT). The opinion of users is extracted from their written text on social media such as comments, tweets, blogs, feedbacks etc. and are classified as positive or negative opinion based on sentiment score of SMT using dictionary-based approach and a binary classifier. The dictionary-based approach uses opinion verb dictionary (OVD) to extract the sentiment of opinion verbs present in SMT. This OVD contain only opinion verbs along with their sentiment score. The various steps of the framework such as lower-case conversion, tokenization, spell checker, Part-of-Speech tagging, stop word elimination, stemming, sentiment score calculation, and classification of SMT has been discussed. A new concept of threshold negative parameter is first time introduced in this article. In the experiment, the proposed SentiVerb system’s performance is evaluated on three datasets such as Facebook comments on goods and services tax (GST) implementation in India, tweets on the debate between former president of USA Mr. Barack Obama and Mr. John McCain, and the movie reviews. Consequently, the implementation of the proposed SentiVerb system using rule-based classifier (RBC) gives the best performance result in term of accuracy with 82.5% on GST comments and 79.18% on Obama-McCain debate, which is better than the existing algorithms on the social issues related domain dataset(s). Also, system performance (accuracy of 71.3%) is better than others results on standard movie dataset.

     

Camtasia in the Classroom: Student Attitudes and Preferences for Video Commentary or Microsoft Word Comments During the Revision Process

In the last ten years, libraries, individual departments, and professors have experimented with screen-capture software to develop edited tutorials, record in-class lectures via presentation software, and record think-aloud rationale for difficult problem sets. Moreover, screen-capture software has been used to provide visual/audio feedback for student writing. Currently, there is scant research on visual/audio feedback via screen-capture software in writing courses. The present study examines student perceptions and attitudes about two different modes and media of teacher feedback: Microsoft Word comments versus visual/audio commentary. The results indicate that the mode and medium of teacher feedback had an impact on students’ perceptions about the rhetorical context of the revision process and perceptions about the teacher/student relationship. Students who preferred the visual/audio modality of the teacher commentary videos cited their conversational quality, clarification of expectations, and reference to more global issues in writing. On the other hand, students who preferred the Microsoft Word comments were more apt to discuss its indexical quality in that students could easily revise surface level features or locate the “problem” sentence. The results also indicate that an either/or approach to teacher feedback is not necessary. Students articulated the relevance of using a combination approach in which Microsoft Word comments and the teacher commentary videos could be used for different elements or stages of the writing process. As instructors transition to teaching within online contexts and experiment with new technologies, it is important to examine the significance of the mode and medium of teacher feedback in student perceptions, participation, and writing practices.     

A non-linear quality improvement model using SVR for manufacturing TFT-LCDs

Thin Film Transistor??Liquid Crystal Displays (TFT-LCDs) are widely used in TVs, monitors, and PDAs. The key process of producing a TFT-LCD is using alignment to combine a Thin Film Transistor (TFT) panel with a Color Filter (CF) panel, which is called ??celling??. The defined cell vernier, which indicates the alignment error, is an important quality index in the manufacturing process. In the CF manufacturing process, the cell vernier is difficult to control because it depends on six TPEs (Total Pitch Errors), with each TPE highly dependent on the others. This paper aims to improve the cell vernier forecasting model with the six TPE attributes to enhance the production yield in the CF manufacturing process. Using the six dependent variables, this study found that the SVR (Support Vector Machine for Regression) model is the fittest for generating quality results that meet the designed specifications.     

The effect of different social media marketing channels and events on movie box office: An elaboration likelihood model perspective

Social media has become an important marketing media to attract and retain consumers. This article focuses on the movie industry and aims to investigate how different channels and events in social media marketing achieve box office success through different consumers’ responses. In reference to elaboration likelihood model (ELM), we propose our research model and test hypotheses using the data of 304 movies with the information of box office, attributes, and associated social media posts. The results show that: (1) official microblog activity increases the purchase intent through changing audience's attitude while third-party mention increases purchase intent through catching audience's attention and promoting positive attitude, and there is an interaction effect between official microblog and third-party media; (2) social media marketing events related to contents introduction promote purchase intent through central route while those related to surrounding information promote purchase intent through peripheral route; and (3) movie attributes interact with marketing intensity in affecting purchase intent. Under the same marketing intensity, the marketing effect of domestic sequel movies released on popular holidays is better. Our findings provide both theoretical and practical implications.     

基于条件随机场的评价对象缺省项识别

在电商网站评论文本中,评价对象和评价属性的缺省识别对文本情感分析具有重要地作用。针对电商网站评论文本中评价对象和评价属性缺省问题,该文提出了一种基于条件随机场的评价对象缺省项识别方法。首先利用情感词典识别观点句,将缺省项识别问题转换成序列标注问题,综合词法特征和依存句法特征,使用条件随机场模型进行训练,并在测试集上对待识别的观点句进行序列标注,通过标注结果判定缺省项的位置。实验结果表明,该方法具有较高的准确率和召回率,验证了该方法的有效性。     

针对复杂用户评论的代码质量属性判断

随着开发者社区和代码托管平台成为程序员获取代码的主要途径,针对代码的用户评论数量急剧增加.用户在使用代码后给出的评论中包含多种静态和动态的代码质量属性信息,但由于用户评论多为复杂句,使得评论中包含的代码质量属性难以判断.针对复杂用户评论的代码质量属性判断将有助于分析用户评论中的代码质量信息,有助于开发者在了解用户的代码使用情况和用户关注的代码质量属性后有针对性地提升代码质量.提出了针对复杂用户评论的代码质量属性判断方法.首先对复杂用户评论进行分句并构建分句的依存句法关系有向图;然后,应用基于分句的依存句法关系的主题判断规则抽取分句中的主题;接着,根据初始的代码质量属性特征词库识别各主题对应的代码质量属性,并获取各主题的代码质量属性表现与表现结果;最后,基于主题处理规则分析复杂用户评论中的代码质量属性表现与表现结果,产生复杂用户评论中代码质量属性相关结果,并持续扩充初始代码质量属性特征词库.实验结果表明,论文方法能够对复杂用户评论的代码质量属性进行有效判断.     

基于本体特征的影评细粒度情感分类

针对中文影评情感分类中缺少特征属性及情感强度层面的粒度划分问题,提出一种基于本体特征的细粒度情感分类模型。首先,利用词频逆文档频率（TF-IDF）和TextRank算法提取电影特征,构建本体概念模型。其次,将电影特征属性和普鲁契克多维度情绪模型与双向长短时记忆网络（Bi-LSTM）融合,构建了在特征粒度层面和八分类情感强度下的细粒度情感分类模型。实验中,本体特征分析表明：观影人对故事属性关注度最高,继而是题材、人物、场景、导演等特征;模型性能分析表明：基于特征粒度和八分类情感强度,与应用情感词典、机器学习、Bi-LSTM网络算法在整体粒度和三分类情感强度层面的其他5个分类模型相比,该模型不仅有较高的F1值（0.93）,而且还能提供观影人对电影属性的情感偏好和情感强度参考,实现了中文影评更细粒度的情感分类。