Subjects: Library Science，Information Science >> Information Science submitted time 2023-04-01 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] We put forward an explainable personalized recommendation method based on adjustment of users' long- and short-preferences in view of the current problems that increasingly complexity and more feature data inputs of recommendation models, low interpretability of traditional recommendation models and over-specialization of recommendation results.[Method/process] We constructed a user preference model from two dimensions of users' recent product needs and their long-term lifestyles, used the user's rating bias and attention mechanism for reference, combined the user's long- and short-term preference with their direct score to predict the score of unknown items, and formed the Top-N recommendations.[Result/conclusion] The experimental results on two datasets showed that our method had a good performance to different user behaviors (explicit feedback or implicit feedback), different number of Top-N recommended items, and in different recommendation algorithms. It improves the accuracy, recall and diversity of the recommendation results without making great changes to various recommendation models, and based on the change of long- and short-term preference coefficients, it realizes the adjustment to the diversity and accuracy of the recommendation results, and form the corresponding recommended explanation.
Subjects: Library Science，Information Science >> Information Science submitted time 2023-04-01 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] There may be substitutability and complementarity between shared accommodation and hotel reservation platforms. However, there is still a lack of discussion on which products and services this kind of substitutability and complementarity are embodied in. Therefore, a cross-platform comparative analysis is needed.[Method/process] In this paper, 86 635 reviews of relevant rental rooms in Beijing were collected from Ctrip.com and Xiaozhu.com. The cross-platform comparative analysis of online reviews is further carried out by integrated latent dirichlet allocation (LDA), social network analysis (SNA) and sentiment analysis.[Result/conclusion] The study found the similarities and differences of the two platforms' users in the comment theme, social network and the emotion of each topic, and further explained the substitutability and complementarity of the two platforms in products and services from the perspective of users' online reviews. The results of this paper also provide important practical reference for platform managers to develop and improve accommodation products and services.
Subjects: Agriculture, Forestry,Livestock & Aquatic Products Science >> Basic Disciplines of Agriculture submitted time 2017-11-06 Cooperative journals: 《中国生态农业学报》
Abstract：基于青藏高原及周边107 个气象站点1965—2013 年逐月气温、降水及日照时数等气象数据, 分析了 1965 年以来青藏高原区的气候变化趋势, 并采用MODIS 数据、Thornthwaite Memorial 模型及GIS 技术分析了近50 a 青藏高原牧草气候生产潜力及其时空变化特征; 利用连续22 a 的青藏高原牧草生育期观测数据, 探讨了牧草生育期的时空变化特征及气象因子与牧草主要发育期的关系。结果表明: 1)近50 a 青藏高原平均气温呈上升趋势, 升温幅度达0.53 ℃(10a)1, 降水量总体呈现上升趋势, 但增加幅度较小, 其倾向率为7.81 mm(10a)1; 而日照时数呈下降趋势, 其下降幅度为16.94 h(10a)1。2)1965—2013 年青藏高原牧草气候生产潜力总体呈增加趋势, 在空间上, 由西北向东南依次增加, 青海省北部及南部部分地区气候生产潜力上升幅度较大, 而西藏东部上升幅度较小, 且南北部地区差异较大。3)牧草返青期、抽穗期及开花期均呈提前趋势, 而黄枯期呈现推迟趋势, 从而延长了牧草物候期; 由东南向西北牧草返青期逐渐推迟, 而黄枯期主要出现在一年中的第257~289 d,其空间整体差异不如返青期明显。4)温度和降水均与牧草物候期呈显著正相关, 而日照时数与其呈显著负相关,且温度是影响牧草物候期变化的主要因子。利用青藏高原牧草生产潜力及物候期与气候因子的响应规律, 可为提高该区牧草的实际产量和保护青藏高原草地生态系统提供借鉴和依据。
Subjects: Other Disciplines >> Synthetic discipline submitted time 2023-10-09 Cooperative journals: 《心理科学进展》
Abstract： Short video indulgence refers to an individual’s compulsive and uncontrollable consumption of short videos, leading to significant behavioral or attention impairments, and subsequently causing difficulties in interpersonal relationships, learning, and/or work adaptation. With the continuous expansion of the short video user base and the trend towards younger groups, threats of short video indulgence to users’ physical and mental health have aroused extensive attention. From a human-computer interaction perspective, we synthesized and delineated the relevant factors contributing to the occurrence of short video indulgence. The objective is to formulate a comprehensive framework delineating the intricate mechanism that underpins the phenomenon of short video indulgence, thereby shedding light on the intricacies involved in its developmental process. At first, in order to explore the delineation between short video usage and indulgence, we categorized short video usage into “instrumental” and “ritualistic” forms. Instrumental usage refers to user behavior driven by specific goals or needs, where short videos serve as tools or means to achieve particular objectives. Ritualistic usage refers to user behavior without a specific objective, where short videos become habitual behaviors associated with particular contexts, times, or situations. The transition from conventional utilization of short videos to the state of short video indulgence appears to encompass a notable shift in usage behavior, evolving from a utilitarian “instrumental” function to a more “ritualistic” engagement.After that, the present work formulates a conceptual framework delineating the mechanisms underlying the onset of short video indulgence, delving into the domains of human-computer interaction and susceptibility traits. The first section encompasses four facets: information technology, content provision, human-computer interaction, and user experience. Their salient characteristics encompass technological advancement, content richness, interactive efficiency, and user immersion. Furthermore, propelled by recommendation algorithms, users’ engagement with short videos becomes increasingly fortified. The second section systematically expounds the susceptibility factors contributing to short video indulgence. The four categories of unique susceptibility traits align with the four stages of interactive mechanisms, while the categories represented by common susceptibility traits have an inducing effect on general addictive behaviors. Considering the analogous nature of short video indulgence to general online indulgence, the unique and common susceptibility traits exhibit mutual intersection and overlap. Overall, the role of interactive mechanisms lies in arousing susceptibility traits, rendering individuals more susceptible to allure and ensnarement in a cycle of addictive behaviors. Simultaneously, susceptibility traits amplify users’ responsiveness and vulnerability to inducing factors. The multifaceted components within the realm of human-computer interaction, propelled by recommendation algorithms, intricately intertwine with users’ susceptibility traits, driving the transformation of users’ engagement with short videos from an “instrumental” to a “ritualistic” approach, ultimately leading to the emergence of short video indulgence. This framework seeks to illuminate the genesis and progression of short video indulgence, offering researchers in this domain a comprehensive conceptual structure to foster the scientific governance of short video indulgence.Subsequently, in order to achieve a deeper understanding of the mechanism behind short video indulgence, we offered theoretical interpretations of short video indulgence from cognitive, emotional, motivational, and social perspectives. The dual process theory, opponent process theory, uses and gratifications theory and social shaping of technology theory were employed to elucidate the process of short video indulgence formation.Finally, this study concludes by summarizing the existing shortcomings in the current field of research. The points are concluded as follows: 1) The research methods are limited, there should be a diversification of research perspectives; 2) Insufficient attention to technology emphasizes the need to emphasize improvements in technology that contribute to addiction; 3) The mechanism of formation is unclear, there should be a deepening of the research into the mechanisms of occurrence; 4) Inadequate research on user characteristics highlights the need to focus on susceptibility factor studies.
Subjects: Psychology >> Developmental Psychology Subjects: Psychology >> Applied Psychology submitted time 2023-08-12
Abstract： Short video indulgence refers to an individual’s compulsive and uncontrollable consumption of short videos, leading to significant behavioral or attention impairments, and subsequently causing difficulties in interpersonal relationships, learning, and/or work adaptation. With the continuous expansion of the user base and the increasing prevalence among younger demographics, the potential threat of short video indulgence has garnered attracted widespread attention. Employing a human-computer interaction framework, this study first categorizes short video usage into “instrumental” and “ritualistic” forms. Subsequently, through a comprehensive considering of interaction process and users’ susceptibility traits, a conceptual framework was constructed to elucidate the mechanisms underlying short video indulgence. Finally, theoretical exposition of short video indulgence was presented from cognitive, emotional, motivational, and social vantage points. Future researchers are expected to focus on the mechanism of the occurrence of short video indulgence, emphasize the media characteristics and technical properties that provoke indulgence, and work to advance the prevention and intervention of short video indulgence.
Subjects: Library Science，Information Science >> Information Science submitted time 2017-12-05 Cooperative journals: 《数据分析与知识发现》
Abstract：【目的】识别并获取细粒度的用户偏好信息, 优化图书个性化推荐的效果。【方法】使用情感分析方法对 用户图书评论进行属性层文本挖掘, 通过用户本身的图书评论获取用户对图书属性的偏好; 基于每本图书的所 有评论的情感计算获得其属性评分; 将用户偏好矩阵、图书属性得分矩阵进行匹配, 从而实现用户对图书属性情 感偏好的个性化推荐。【结果】利用亚马逊图书评论数据作为数据来源分别对传统的协同过滤方法与本文提出的 推荐方法进行实验对比。结果表明, 本文提出的方法在准确性、召回率、覆盖率上分别提高了 0.030、0.097、0.2812。 【局限】未考虑时间因素对用户偏好的影响, 并且属性类型的全面程度受亚马逊图书评论数量和质量的限制。 【结论】本文计算用户对图书属性的情感得分, 得到细粒度的用户偏好信息, 并通过与图书属性的得分进行匹配, 提升了图书个性化推荐的效果。
Subjects: Library Science，Information Science >> Information Science submitted time 2017-11-30 Cooperative journals: 《数据分析与知识发现》
Abstract：【目的】识别并获取细粒度的用户偏好信息, 优化图书个性化推荐的效果。【方法】使用情感分析方法对 用户图书评论进行属性层文本挖掘, 通过用户本身的图书评论获取用户对图书属性的偏好; 基于每本图书的所 有评论的情感计算获得其属性评分; 将用户偏好矩阵、图书属性得分矩阵进行匹配, 从而实现用户对图书属性情 感偏好的个性化推荐。【结果】利用亚马逊图书评论数据作为数据来源分别对传统的协同过滤方法与本文提出的 推荐方法进行实验对比。结果表明, 本文提出的方法在准确性、召回率、覆盖率上分别提高了 0.030、0.097、0.2812。 【局限】未考虑时间因素对用户偏好的影响, 并且属性类型的全面程度受亚马逊图书评论数量和质量的限制。 【结论】本文计算用户对图书属性的情感得分, 得到细粒度的用户偏好信息, 并通过与图书属性的得分进行匹配, 提升了图书个性化推荐的效果。
Subjects: Biology >> Ecology submitted time 2017-10-30 Cooperative journals: 《生态学报》
Abstract：随着生活质量的提高，我国农村居民生活能源消费呈现大幅增长的趋势，成为碳排放增长的新源泉。估算了我国30个省区2001-2013年的农村居民生活能源碳排放，采用碳基尼系数、ArcGIS技术分析了中国省级尺度农村居民生活能源碳排放的时空特征，并利用STIRPAT模型辨明了农村居民生活能源碳排放的主要影响因素。结果表明：（1）2001-2013年农村居民直接生活能源碳排放量和间接生活能源碳排放量分别增长了7.65%、9.16%。（2）东部、中部、西部地区的碳基尼系数呈下降趋势，说明各区域农村居民人均生活能源碳排放量的区域差异总体均呈缩小趋势。（3）2001-2013年间，处于我国农村居民人均直接生活能源碳排放高水平地区的空间格局分布相对较为稳定，而对于人均间接生活能源碳排放来说，处于低水平地区的空间格局分布较为稳定。（4）农村人口规模、农民人均纯收入、农村居民生活消费支出、青壮年人口比重对农村居民生活能源碳排放量具有促进作用，而农村居民能源消费结构对其具有减缓作用，且北方农村居民生活能源碳排放量明显高于南方。（5）从环境Kuznets曲线假说出发，经济发展是促使我国农村居民生活能源碳排放Kuznets曲线存在拐点的重要因素。
Hits
Hits
Downloads
Comment
YES