User-controllable personalization: A case study with SetFusion

In this research we investigated the role of user controllability on personalized systems by implementing and studying a novel interactive recommender interface, SetFusion. We examined whether allowing the user to control the process of fusing or integrating different algorithms (i.e., different sources of relevance) resulted in increased engagement and a better user experience. The essential contribution of this research stems from the results of a user study (N=40) of controllability in a scenario where users could fuse different recommendation approaches, with the possibility of inspecting and filtering the items recommended. First, we introduce an interactive Venn diagram visualization, which combined with sliders, can provide an efficient visual paradigm for information filtering. Second, we provide a three-fold evaluation of the user experience: objective metrics, subjective user perception, and behavioral measures. Through the analysis of these metrics, we confirmed results from recent studies, such as the effect of trusting propensity on accepting the recommendations and also unveiled the importance of features such as being a native speaker. Our results present several implications for the design and implementation of user-controllable personalized systems.     

Motion parallax from head movement enhances stereoscopic displays by improving presence and decreasing visual fatigue

Virtual reality has advanced significantly recent years. Public attention and most academic studies of late have centered on head-worn VR. However, there are other VR modalities, and different modalities may be suitable in different situations. In this paper, we investigate Fish Tank Virtual Reality (FTVR) systems, which is close to readiness to be part of our everyday lives. In particular, stereoscopic displays and head tracking systems, some of the most important hardware components of FTVR systems, are now widespread commodities. This means that FTVR may soon become a platform for everyday applications. However, further understanding of the capabilities, limitations, and human factors of FTVR systems using modern commodity hardware is critical to the adoption of FTVR. Since one of the most important aspects of a FTVR system is how well it provides a sense of presence to users, we present a study that explores the role of motion parallax when combined with stereopsis in a FTVR system. We measure fatigue and subjective perception of presence using standard questionnaires. We find that users receiving both cues have lower visual fatigue and higher ratings for presence than those receiving stereo cues only. Measurements of participants’ head movement during each task prove valuable in explaining the experimental findings. We conclude that motion parallax is important for enhancing user experience by lowering visual fatigue and increasing users’ subjective perception of presence.     

Data-driven models for timing feedback responses in a Map Task dialogue system

Traditional dialogue systems use a fixed silence threshold to detect the end of users’ turns. Such a simplistic model can result in system behaviour that is both interruptive and unresponsive, which in turn affects user experience. Various studies have observed that human interlocutors take cues from speaker behaviour, such as prosody, syntax, and gestures, to coordinate smooth exchange of speaking turns. However, little effort has been made towards implementing these models in dialogue systems and verifying how well they model the turn-taking behaviour in human–computer interactions. We present a data-driven approach to building models for online detection of suitable feedback response locations in the user's speech. We first collected human–computer interaction data using a spoken dialogue system that can perform the Map Task with users (albeit using a trick). On this data, we trained various models that use automatically extractable prosodic, contextual and lexico-syntactic features for detecting response locations. Next, we implemented a trained model in the same dialogue system and evaluated it in interactions with users. The subjective and objective measures from the user evaluation confirm that a model trained on speaker behavioural cues offers both smoother turn-transitions and more responsive system behaviour.     

WSAM:互联网UGC文本主观观点挖掘系统

互联网上的用户生成内容UGC(User Generated Content)中蕴含的用户主观观点信息对分析用户行为、用户需求等工作有着重要的价值。设计一套基于自然语言理解的互联网UGC文本主观观点分析系统WSAM,该系统能挖掘出用户主观观点所蕴含的关注对象和主观成分。分析了互联网UGC现象和生成原因,总结出UGC中用户主观观点中的四种主要类型。挖掘用户主观观点过程中,将用户主观观点的挖掘转化为句子中主观观点关注对象的识别和主观成分的判断。算法结合基于词语类、结构类等相关特征,采用最大熵分类器挖掘用户主观观点。实验验证,WSAM系统所采用的算法性能较好,且还能够灵活扩充出情感分析(Opin-ion Mining)等相关应用,同样也能达到较好的结果。     

Seeing eye to eye? An exploratory study of free open source software users’ perceptions

This study develops a typology that permits the classification of free open source software (FOSS) users into market segments. Based on the typology the nature and extent of perception differences between core FOSS users and FOSS users in other market segments is examined. Significant perception differences are observed between users in different market segments. Consequently, the potential barriers to FOSS adoption are identified and recommendations that may drive greater FOSS adoption are proposed.     

基于好友亲密度的用户匹配

用户匹配的目的是检测来自不同社交网络的用户是否是同一个人.现有的研究主要集中在用户属性和网络嵌入上,而这些研究方法往往忽略了用户与好友间的亲密关系.因此,文中提出一种基于好友亲密度的用户匹配算法(FCUM).该算法是一种半监督、端到端的跨社交网络用户匹配算法,其中注意力机制被用于量化用户与好友之间的亲密度.好友亲密度的...     

Linking objective design factors with subjective aesthetics: An experimental study on how structure and color of websites affect the facets of users’ visual aesthetic perception

The present study examines how objective design factors of a website are linked to different facets of subjective aesthetic perception. Five online experiments based upon the screenshots of real-existing websites with a total of N = 194 participants were conducted to isolate and analyze the effects of two objective structural factors (vertical symmetry, visual complexity) and three objective color factors (hue, saturation, brightness) on the different facets of subjective aesthetic perception (simplicity, diversity, colorfulness, craftsmanship) measured with the Visual Aesthetics of Website Inventory (Moshagen & Thielsch, 2010). Although all investigated factors are apparent features in website design, their effects on different facets of subjective aesthetic perception are not yet well understood. Our results show that websites of high symmetry, low complexity, blue hue, medium brightness or medium and high saturation received the highest overall aesthetics ratings. Furthermore, data reveal that structural factors compared to color factors have a manifold and greater impact on the different facets of subjective aesthetic perception than the color factors. Both structural factors have a great impact on simplicity, diversity and craftsmanship whereas the color factors have a great impact especially on colorfulness. Only complexity affects all facets of subjective aesthetic perception. The other objective design factors had effects on specific facets. Our findings shed light on the relationship between objective and subjective factors of aesthetic perception and may help designers to systematically target specific facets of visual aesthetics.     

The uses and gratifications of using Facebook music listening applications

Despite rapid adoption of social media as a means of music listening, little is known about users’ motivations. This study applies the uses and gratifications approach to users’ motivations for using music listening applications on Facebook. Participants completed an online survey, and 153 out of 576 respondents indicated that they used a Facebook music listening application. A principal axis factor analysis identified three different motivations for this usage, namely entertainment, communication, and habitual diversion gratifications. The entertainment and communication gratifications replicate those found in prior uses and gratifications research concerning other social networking features, illustrating the strong similarity between uses of music and social media. However, the habitual diversion gratification may serve to distinguish listening applications from other features. Identifying and explaining these factors is relevant to social media users, musicians and application designers, as they explain what motivates a means of music listening that is gaining prominence.     

Assessment of the subjective perception of music quality using psychoacoustic approach

It is generally agreed that sound quality is one of the most difficult to measure characteristics of an electroacoustic products such as an earphone or a loudspeaker. A conventional approach used to measure people's subjective perception of these sound reproduction products is to conduct a jury test on a group of experiment participants; however, jury tests require considerable costs, including those of effort and time. As development speed and cost become strategic competitive dimensions, electroacoustic industry needs a more efficient approach to assess their newly developed products for subjective sound quality. This study developed and validated a quantitative model, the tonal harmony level (THL), that can effectively predict people's subjective perceptions of music quality. Participants' subjective perception and preference was measured for four music genres by listening to short music excerpts (8 s) in both ordinal and interval scales. The purpose of using two scales is to examine the consistency between subjective perceptions and to determine the robustness of the subjective measurements. The experimental results were very stable over the two assessment procedures, and the objective THL measure is highly correlated to subjective preference. The analysis suggests that the construction of subjective music quality prediction models should also consider music genre. Among four types of music, musical solos consisted of human vocals accompanied by a few instruments has a distinct pattern from the other three types. Thus, while R² value of the overall regression model is 0.707, the R² values are 0.955 and 0.901 when four music genres are categorized into two groups according to their patterns. When efficiency and accuracy were simultaneously considered, according to the results of this study, the approach of two-group categorization can be adopted.     

Analysis of Minimum Distances in High-Dimensional Musical Spaces

We propose an automatic method for measuring content-based music similarity, enhancing the current generation of music search engines and recommended systems. Many previous approaches to track similarity require brute-force, pair-wise processing between all audio features in a database and therefore are not practical for large collections. However, in an Internet-connected world, where users have access to millions of musical tracks, efficiency is crucial. Our approach uses features extracted from unlabeled audio data and near-neigbor retrieval using a distance threshold, determined by analysis, to solve a range of retrieval tasks. The tasks require temporal features-analogous to the technique of shingling used for text retrieval. To measure similarity, we count pairs of audio shingles, between a query and target track, that are below a distance threshold. The distribution of between-shingle distances is different for each database; therefore, we present an analysis of the distribution of minimum distances between shingles and a method for estimating a distance threshold for optimal retrieval performance. The method is compatible with locality-sensitive hashing (LSH)-allowing implementation with retrieval times several orders of magnitude faster than those using exhaustive distance computations. We evaluate the performance of our proposed method on three contrasting music similarity tasks: retrieval of mis-attributed recordings (fingerprint), retrieval of the same work performed by different artists (cover songs), and retrieval of edited and sampled versions of a query track by remix artists (remixes). Our method achieves near-perfect performance in the first two tasks and 75% precision at 70% recall in the third task. Each task was performed on a test database comprising 4.5 million audio shingles.     

Music recommendation using text analysis on song requests to radio stations

Recommending appropriate music to users has always been a difficult task. In this paper, we propose a novel method in recommending music by analyzing the textual input of users. To this end, we mine a large corpus of documents from a Korean radio station’s online bulletin board. Each document, written by the listener, is composed of a song request associated with a brief, personal story. We assume that such stories are closely related with the background of the song requests and thus, our system performs text analysis to recommend songs that were requested from other similar stories. We evaluate our system using conventional metrics along with a user evaluation test. Results show that there is close correlation between document similarity and song similarity, indicating the potential of using text as a source to recommending music.     

Music snippet extraction via melody-based repeated pattern discovery

In this paper, we present a complete set of procedures to automatically extract a music snippet, defined as the most representative or the highlighted excerpt of a music clip. We first generate a modified and compact similarity matrix based on selected features and distance metrics, and then several improved techniques for music repeated pattern discovery are utilized because a music snippet is usually a part of the repeated melody, main theme or chorus. During the process, redundant and wrongly detected patterns are discarded, boundaries are corrected using beat information, and final clusters are also further sorted according to the occurrence frequency and energy information. Subsequently, following our methods, we designed a music snippet extraction system which allows users to detect snippets. Experiments performed on the system show the superiority of our proposed approach. Supported by the National Natural Science Foundation of China (Grant No. 60873098)     

Improving music recommendation by incorporating social influence

In the past decades, a large number of music pieces are uploaded to the Internet every day through social networks, such as Last.fm, Spotify and YouTube, that concentrates on music and videos. We have been witnessing an ever-increasing amount of music data. At the same time, with the huge amount of online music data, users are facing an everyday struggle to obtain their interested music pieces. To solve this problem, music search and recommendation systems are helpful for users to find their favorite content from a huge repository of music. However, social influence, which contains rich information about similar interests between users and users’ frequent correlation actions, has been largely ignored in previous music recommender systems. In this work, we explore the effects of social influence on developing effective music recommender systems and focus on the problem of social influence aware music recommendation, which aims at recommending a list of music tracks for a target user. To exploit social influence in social influence aware music recommendation, we first construct a heterogeneous social network, propose a novel meta path-based similarity measure called WPC, and denote the framework of similarity measure in this network. As a step further, we use the topological potential approach to mine social influence in heterogeneous networks. Finally, in order to improve music recommendation by incorporating social influence, we present a factor graphic model based on social influence. Our experimental results on one real world dataset verify that our proposed approach outperforms current state-of-the-art music recommendation methods substantially.

     

Adaptively browsing image databases with PIBE

Browsing large image collections is a complex and often tedious task, due to the semantic gap existing between the user subjective notion of similarity and the one according to which a browsing system organizes the images. In this paper we propose PIBE, an adaptive image browsing system, which provides users with a hierarchical view of images (the Browsing Tree) that can be customized according to user preferences. A key feature of PIBE is that it maintains local similarity criteria for each portion of the Browsing Tree. This makes it possible both to avoid costly global reorganization upon execution of user actions and, combined with a persistent storage of the Browsing Tree, to efficiently support multiple browsing tasks. We present the basic principles of PIBE and report experimental results showing the effectiveness of its browsing and personalization functionalities.     

融合用户评分与显隐兴趣相似度的协同过滤推荐算法

协同过滤算法是推荐系统中使用最广泛的算法,其核心是利用某兴趣爱好相似的群体来为用户推荐感兴趣的信息。传统的协同过滤算法利用用户-项目评分矩阵计算相似度,通过相似度寻找用户的相似群体来进行推荐,但是由于其评分矩阵的稀疏性问题,对相似度的计算不够准确,这间接导致推荐系统的质量下降。为了缓解数据稀疏性对相似度计算的影响并提高推荐质量,提出了一种融合用户评分与用户显隐兴趣的相似度计算方法。该方法首先利用用户-项目评分矩阵计算用户评分相似度;然后根据用户基本属性与用户-项目评分矩阵得出项目隐性属性;之后综合项目类别属性、项目隐性属性、用户-项目评分矩阵和用户评分时间,得到用户显隐兴趣相似度;最后融合用户评分相似度和用户显隐兴趣相似度得到用户相似度,并以此相似度寻找用户的相似群体以进行推荐。在数据集Movielens上的实验结果表明,相比传统算法中仅使用单一的评分矩阵来计算相似度,提出的新相似度计算方法不仅能够更加准确地寻找到用户的相似群体,而且还能够提供更好的推荐质量。     

What Interactivity Means to the User Essential Insights into and a Scale for Perceived Interactivity

The selection and use of media depend largely on how users perceive such media. A central aspect of the “new media” is their interactivity, but how users perceive this phenomenon has rarely been researched. This study provides an in‐depth investigation into the perception component of interactivity and develops a compact scale for its measurement. According to psychological approaches, practical uses (affordances) – not physical or technical characteristics – guide perception. While existing scales mostly measure whether the “interactive” technical features of devices or websites are noticed, our instrument is based on the affordances that interactivity provides. Consequently, a new research design, the use‐identified meaning, was implemented. This is the first study on interactivity that empirically examines a wide range of Internet‐based services, thus meeting the broad ambit of interactivity. Our results generally validate the existing constructs, which are largely based on technical characteristics, yet provide additional insights into the relevant contexts and the subjective significance of different aspects of interactivity.     

Perceptions of system development failures

According to the expectation failure theory, information system failures can occur during development or during system use and may be viewed differently by various stakeholder groups. This premise is examined via a survey of system developers and system users about their perception of frequency of system development problems. The data indicates that users and developers of information systems perceive certain problems at different levels of occurrence.     

案例推理变权值引擎模型及权值计算方法

在案例推理（CBR）案例检索匹配中,不同案例通常由不同的特征构成。而传统的CBR引擎模型大多采用固定权值模式,导致系统在匹配精度方面的性能很低。为了解决这一问题,提出一种CBR变权值引擎模型,在其特征权值计算模块引入人机互动机制,基于群决策法计算主观权值,提出依据专家个体和群体决策差异的主观权值调整方法;基于相似粗糙集法计算客观权值。最后设计了一种综合权值调整算法,通过计算主观权值和客观权值间的距离,判断两者的偏离程度,从而推导出权值调整系数,得到最终的权值调整结果。通过网络攻击案例进行的算例分析和仿真实验验证了上述方法的正确性和优越性。     

基于TV-L1结构纹理分解的图像融合质量评价算法

为对图像融合算法进行客观准确的综合评价,提出一种基于总变差正则化（TV-L¹）结构纹理分解的评价算法。根据对人类视觉系统的研究,可知人们对图像质量的感知主要来自图像底层视觉特征,而结构特征以及纹理特征是最重要的图像底层视觉特征,但目前的图像融合质量评价算法并没有利用这两种特征来进行评价。鉴于此,将图像进行二级结构和纹理分解,根据结构和纹理图像蕴含图像特征的不同,从结构图像和纹理图像两方面分别进行相似度评价,综合各级得分得到最终的评价总得分。基于30幅图像的数据集和8种主流融合算法,参照已有的11种客观评价指标,用波达计数法和肯德尔系数检验了该评价指标的一致性,另外在主观评价图像集上验证了该客观评价指标与主观评价的一致性。