Novel groundtruth transformations for the aesthetic assessment problem

Aesthetic assessment evaluates the quality of a given image using subjective annotations, commonly user ratings, as a knowledge base. Rating complexity is usually relaxed in state-of-the-art works by employing a binary high/low quality label computed from the mean value of rating votes. Nevertheless, this approach introduces uncertainty to average-quality images, which may affect the performance of machine learning models trained from annotated data.In this work, we present a novel approach to aesthetic assessment based on redefining the rating-based groundtruths present in most datasets. Our intent is twofold: to reduce the rating uncertainty and to automatically group them into clusters reflecting high and low quality patterns, thus avoiding an arbitrary threshold like 5 in 1–10 ratings. The experimentation uses the well-known AVA dataset, which consists of more than 255,000 images, and we train several CNN models to test our new groundtruths against the baseline ones. The results show that our approach achieves significant performance gains, between 3% and 9% more balanced accuracy than the baseline groundtruths.     

From statistical methods to deep learning,automatic keyphrase prediction: A survey

Keyphrase prediction aims to generate phrases (keyphrases) that highly summarizes a given document. Recently, researchers have conducted in-depth studies on this task from various perspectives. In this paper, we comprehensively summarize representative studies from the perspectives of dominant models, datasets and evaluation metrics. Our work analyzes up to 167 previous works, achieving greater coverage of this task than previous surveys. Particularly, we focus highly on deep learning-based keyphrase prediction, which attracts increasing attention of this task in recent years. Afterwards, we conduct several groups of experiments to carefully compare representative models. To the best of our knowledge, our work is the first attempt to compare these models using the identical commonly-used datasets and evaluation metric, facilitating in-depth analyses of their disadvantages and advantages. Finally, we discuss the possible research directions of this task in the future.     

A novel framework for deep knowledge tracing via gating-controlled forgetting and learning mechanisms

In this paper, we propose a framework called Gating-controlled Forgetting and Learning mechanisms for Deep Knowledge Tracing (GFLDKT for short). In GFLDKT, two gating-controlled mechanisms are designed to model explicitly forgetting and learning behaviors in students’ learning process. With the designed gating-controlled mechanisms, both the interaction records and students’ different backgrounds are combined effectively for tracing the dynamic changes of students’ mastery of knowledge concepts. Results from extensive experiments demonstrate that the proposed framework outperforms the state-of-the-art models on the KT task. In addition, the ablation study shows that designed forgetting and learning mechanisms contribute clearly to the performance improvement of GFLDKT.     

基于检验检测-服务质量-长短期记忆网络-情感分析模型的检验检测服务质量评价研究

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。     

News-based business sentiment and its properties as an economic index

This paper presents an approach to measuring business sentiment based on textual data. Business sentiment has been measured by traditional surveys, which are costly and time-consuming to conduct. To address the issues, we take advantage of daily newspaper articles and adopt a self-attention-based model to define a business sentiment index, named S-APIR, where outlier detection models are investigated to properly handle various genres of news articles. Moreover, we propose a simple approach to temporally analyzing how much any given event contributed to the predicted business sentiment index. To demonstrate the validity of the proposed approach, an extensive analysis is carried out on 12 years’ worth of newspaper articles. The analysis shows that the S-APIR index is strongly and positively correlated with established survey-based index (up to correlation coefficient $r=0.937$) and that the outlier detection is effective especially for a general newspaper. Also, S-APIR is compared with a variety of economic indices, revealing the properties of S-APIR that it reflects the trend of the macroeconomy as well as the economic outlook and sentiment of economic agents. Moreover, to illustrate how S-APIR could benefit economists and policymakers, several events are analyzed with respect to their impacts on business sentiment over time.     

Fair and Explainable Depression Detection in Social Media

Detection at an early stage is vital for the diagnosis of the majority of critical illnesses and is the same for identifying people suffering from depression. Nowadays, a number of researches have been done successfully to identify depressed persons based on their social media postings. However, an unexpected bias has been observed in these studies, which can be due to various factors like unequal data distribution. In this paper, the imbalance found in terms of participation in the various age groups and demographics is normalized using the one-shot decision approach. Further, we present an ensemble model combining SVM and KNN with the intrinsic explainability in conjunction with noisy label correction approaches, offering an innovative solution to the problem of distinguishing between depression symptoms and suicidal ideas. We achieved a final classification accuracy of 98.05%, with the proposed ensemble model ensuring that the data classification is not biased in any manner.