随着软件协同开发技术与社交网络的深度融合,社交化开发范式已成为当前软件创作与生产的重要方式.这一软件开发模型的灵活性与开放性,吸引了大规模的外围贡献者加入到开源社区中,形成了巨大的软件生产力.在开源社区中,这些分布广泛、规...随着软件协同开发技术与社交网络的深度融合,社交化开发范式已成为当前软件创作与生产的重要方式.这一软件开发模型的灵活性与开放性,吸引了大规模的外围贡献者加入到开源社区中,形成了巨大的软件生产力.在开源社区中,这些分布广泛、规模巨大的外围贡献者,主要以一种无组织的松散方式进行协同.他们需要花费大量的时间和精力,在海量的开源项目中寻找到自己真正感兴趣的项目并进行长期贡献.为了提高大规模群体协同的效率,提出一种基于多维特征的开源项目个性化推荐方法(即Repo Like).该方法从开源项目自身流行度、关联项目技术相关度以及大众贡献者之间的社交关联度这3个维度度量开发者和开源项目之间的关联关系,并利用线性组合和Learning To Rank方法构建推荐模型,从而为开发者提供个性化的项目推荐服务.通过大规模的实验,其结果表明:Repo Like在推荐20个候选项目时的推荐命中率超过25%,能够有效地为开发人员提供有价值的推荐服务.展开更多
In recent years,the growing popularity of social media platforms has led to several interesting natural language processing(NLP)applications.However,these social media-based NLP applications are subject to different t...In recent years,the growing popularity of social media platforms has led to several interesting natural language processing(NLP)applications.However,these social media-based NLP applications are subject to different types of adversarial attacks due to the vulnerabilities of machine learning(ML)and NLP techniques.This work presents a new low-level adversarial attack recipe inspired by textual variations in online social media communication.These variations are generated to convey the message using out-of-vocabulary words based on visual and phonetic similarities of characters and words in the shortest possible form.The intuition of the proposed scheme is to generate adversarial examples influenced by human cognition in text generation on social media platforms while preserving human robustness in text understanding with the fewest possible perturbations.The intentional textual variations introduced by users in online communication motivate us to replicate such trends in attacking text to see the effects of such widely used textual variations on the deep learning classifiers.In this work,the four most commonly used textual variations are chosen to generate adversarial examples.Moreover,this article introduced a word importance ranking-based beam search algorithm as a searching method for the best possible perturbation selection.The effectiveness of the proposed adversarial attacks has been demonstrated on four benchmark datasets in an extensive experimental setup.展开更多
将列表级排序学习和推荐算法相结合,能够有效提高传统推荐系统返回结果的准确性。针对社交网络环境,提出一种基于列表级排序学习的推荐算法L2 R2SN (list-wise learning to rank for recommendation for social networks)。从社交网络...将列表级排序学习和推荐算法相结合,能够有效提高传统推荐系统返回结果的准确性。针对社交网络环境,提出一种基于列表级排序学习的推荐算法L2 R2SN (list-wise learning to rank for recommendation for social networks)。从社交网络中挖掘出用户好友潜在的影响特征,以及物品潜在的隐性特征,融入列表级排序学习的推荐模型中,通过梯度下降方法迭代训练模型参数获得模型的最优解,将物品列表中排序较前的top-k个物品推送给用户。多组实验结果表明,L2 R2SN算法能够有效提高推荐结果的准确性,更为有效地反映用户的偏好。展开更多
文摘随着软件协同开发技术与社交网络的深度融合,社交化开发范式已成为当前软件创作与生产的重要方式.这一软件开发模型的灵活性与开放性,吸引了大规模的外围贡献者加入到开源社区中,形成了巨大的软件生产力.在开源社区中,这些分布广泛、规模巨大的外围贡献者,主要以一种无组织的松散方式进行协同.他们需要花费大量的时间和精力,在海量的开源项目中寻找到自己真正感兴趣的项目并进行长期贡献.为了提高大规模群体协同的效率,提出一种基于多维特征的开源项目个性化推荐方法(即Repo Like).该方法从开源项目自身流行度、关联项目技术相关度以及大众贡献者之间的社交关联度这3个维度度量开发者和开源项目之间的关联关系,并利用线性组合和Learning To Rank方法构建推荐模型,从而为开发者提供个性化的项目推荐服务.通过大规模的实验,其结果表明:Repo Like在推荐20个候选项目时的推荐命中率超过25%,能够有效地为开发人员提供有价值的推荐服务.
基金supported by the National Research Foundation of Korea (NRF)grant funded by the Korea government (MSIT) (No.NRF-2022R1A2C1007434)by the BK21 FOUR Program of the NRF of Korea funded by the Ministry of Education (NRF5199991014091).
文摘In recent years,the growing popularity of social media platforms has led to several interesting natural language processing(NLP)applications.However,these social media-based NLP applications are subject to different types of adversarial attacks due to the vulnerabilities of machine learning(ML)and NLP techniques.This work presents a new low-level adversarial attack recipe inspired by textual variations in online social media communication.These variations are generated to convey the message using out-of-vocabulary words based on visual and phonetic similarities of characters and words in the shortest possible form.The intuition of the proposed scheme is to generate adversarial examples influenced by human cognition in text generation on social media platforms while preserving human robustness in text understanding with the fewest possible perturbations.The intentional textual variations introduced by users in online communication motivate us to replicate such trends in attacking text to see the effects of such widely used textual variations on the deep learning classifiers.In this work,the four most commonly used textual variations are chosen to generate adversarial examples.Moreover,this article introduced a word importance ranking-based beam search algorithm as a searching method for the best possible perturbation selection.The effectiveness of the proposed adversarial attacks has been demonstrated on four benchmark datasets in an extensive experimental setup.
文摘将列表级排序学习和推荐算法相结合,能够有效提高传统推荐系统返回结果的准确性。针对社交网络环境,提出一种基于列表级排序学习的推荐算法L2 R2SN (list-wise learning to rank for recommendation for social networks)。从社交网络中挖掘出用户好友潜在的影响特征,以及物品潜在的隐性特征,融入列表级排序学习的推荐模型中,通过梯度下降方法迭代训练模型参数获得模型的最优解,将物品列表中排序较前的top-k个物品推送给用户。多组实验结果表明,L2 R2SN算法能够有效提高推荐结果的准确性,更为有效地反映用户的偏好。
