共查询到20条相似文献，搜索用时 15 毫秒
1.
《Information processing & management》2022,59(4):102953
Aspect-based sentiment analysis technologies may be a very practical methodology for securities trading, commodity sales, movie rating websites, etc. Most recent studies adopt the recurrent neural network or attention-based neural network methods to infer aspect sentiment using opinion context terms and sentence dependency trees. However, due to a sentence often having multiple aspects sentiment representation, these models are hard to achieve satisfactory classification results. In this paper, we discuss these problems by encoding sentence syntax tree, words relations and opinion dictionary information in a unified framework. We called this method heterogeneous graph neural networks (Hete_GNNs). Firstly, we adopt the interactive aspect words and contexts to encode the sentence sequence information for parameter sharing. Then, we utilized a novel heterogeneous graph neural network for encoding these sentences’ syntax dependency tree, prior sentiment dictionary, and some part-of-speech tagging information for sentiment prediction. We perform the Hete_GNNs sentiment judgment and report the experiments on five domain datasets, and the results confirm that the heterogeneous context information can be better captured with heterogeneous graph neural networks. The improvement of the proposed method is demonstrated by aspect sentiment classification task comparison. 相似文献
2.
Ding Xiao Yugang Ji Yitong Li Fuzhen Zhuang Chuan Shi 《Information processing & management》2018,54(6):861-873
Aspect mining, which aims to extract ad hoc aspects from online reviews and predict rating or opinion on each aspect, can satisfy the personalized needs for evaluation of specific aspect on product quality. Recently, with the increase of related research, how to effectively integrate rating and review information has become the key issue for addressing this problem. Considering that matrix factorization is an effective tool for rating prediction and topic modeling is widely used for review processing, it is a natural idea to combine matrix factorization and topic modeling for aspect mining (or called aspect rating prediction). However, this idea faces several challenges on how to address suitable sharing factors, scale mismatch, and dependency relation of rating and review information. In this paper, we propose a novel model to effectively integrate Matrix factorization and Topic modeling for Aspect rating prediction (MaToAsp). To overcome the above challenges and ensure the performance, MaToAsp employs items as the sharing factors to combine matrix factorization and topic modeling, and introduces an interpretive preference probability to eliminate scale mismatch. In the hybrid model, we establish a dependency relation from ratings to sentiment terms in phrases. The experiments on two real datasets including Chinese Dianping and English Tripadvisor prove that MaToAsp not only obtains reasonable aspect identification but also achieves the best aspect rating prediction performance, compared to recent representative baselines. 相似文献
3.
Mohammad Tubishat Norisma Idris Mohammad A.M. Abushariah 《Information processing & management》2018,54(4):545-563
Sentiment analysis is a text classification branch, which is defined as the process of extracting sentiment terms (i.e. feature/aspect, or opinion) and determining their opinion semantic orientation. At aspect level, aspect extraction is the core task for sentiment analysis which can either be implicit or explicit aspects. The growth of sentiment analysis has resulted in the emergence of various techniques for both explicit and implicit aspect extraction. However, majority of the research attempts targeted explicit aspect extraction, which indicates that there is a lack of research on implicit aspect extraction. This research provides a review of implicit aspect/features extraction techniques from different perspectives. The first perspective is making a comparison analysis for the techniques available for implicit term extraction with a brief summary of each technique. The second perspective is classifying and comparing the performance, datasets, language used, and shortcomings of the available techniques. In this study, over 50 articles have been reviewed, however, only 45 articles on implicit aspect extraction that span from 2005 to 2016 were analyzed and discussed. Majority of the researchers on implicit aspects extraction rely heavily on unsupervised methods in their research, which makes about 64% of the 45 articles, followed by supervised methods of about 27%, and lastly semi-supervised of 9%. In addition, 25 articles conducted the research work solely on product reviews, and 5 articles conducted their research work using product reviews jointly with other types of data, which makes product review datasets the most frequently used data type compared to other types. Furthermore, research on implicit aspect features extraction has focused on English and Chinese languages compared to other languages. Finally, this review also provides recommendations for future research directions and open problems. 相似文献
4.
《Information processing & management》2023,60(5):103435
Every day millions of news articles and (micro)blogs that contain financial information are posted online. These documents often include insightful financial aspects with associated sentiments. In this paper, we predict financial aspect classes and their corresponding polarities (sentiment) within sentences. We use data from the Financial Question & Answering (FiQA) challenge, more precisely the aspect-based financial sentiment analysis task. We incorporate the hierarchical structure of the data by using the parent aspect class predictions to improve the child aspect class prediction (two-step model). Furthermore, we incorporate model output from the child aspect class prediction when predicting the polarity. We improve the F1 score by 7.6% using the two-step model for aspect classification over direct aspect classification in the test set. Furthermore, we improve the state-of-the-art test F1 score of the original aspect classification challenge from 0.46 to 0.70. The model that incorporates output from the child aspect classification performs up to par in polarity classification with our plain RoBERTa model. In addition, our plain RoBERTa model outperforms all the state-of-the-art models, lowering the MSE score by at least 28% and 33% for the cross-validation set and the test set, respectively. 相似文献
5.
This paper focuses on the role of capabilities in economic development. In recent years, the quality and availability of data on different aspects of development have improved, and this provides new opportunities for investigating the reasons behind the large differences in economic development. Using factor analysis on data for 25 indicators and 115 countries between 1992 and 2004, we identify four different types of “capabilities”: the development of the “innovation system”, the quality of “governance”, the character of the “political system” and the degree of “openness” of the economy. Innovation systems and governance are shown to be of particular importance for economic development. 相似文献
6.
A user study of aNobii was conducted with an aim to exploring possible criteria for evaluating social navigational tools. A set of measures designed to capture various aspects of the benefits provided by the tools was proposed. To test the applicability of these measures, a within-subject experimental design was adopted where fifty regular aNobii users searched alternately with three book-finding tools: browsing “friends’ bookshelves”, “similar bookshelves”, and “books by known authors”. Other than the self-report user experience and search result measures, the “choice set” model was used as a novel framework for navigational effectiveness. Further analyses were conducted to explore whether three aspects of reader preference, “preference insight”, “preference diversity”, and “reading involvement” might influence the performance of the tools. 相似文献
7.
《Information processing & management》2020,57(3):102211
Aspect-based sentiment analysis allows one to compute the sentiment for an aspect in a certain context. One problem in this analysis is that words possibly carry different sentiments for different aspects. Moreover, an aspect’s sentiment might be highly influenced by the domain-specific knowledge. In order to tackle these issues, in this paper, we propose a hybrid solution for sentence-level aspect-based sentiment analysis using A Lexicalized Domain Ontology and a Regularized Neural Attention model (ALDONAr). The bidirectional context attention mechanism is introduced to measure the influence of each word in a given sentence on an aspect’s sentiment value. The classification module is designed to handle the complex structure of a sentence. The manually created lexicalized domain ontology is integrated to utilize the field-specific knowledge. Compared to the existing ALDONA model, ALDONAr uses BERT word embeddings, regularization, the Adam optimizer, and different model initialization. Moreover, its classification module is enhanced with two 1D CNN layers providing superior results on standard datasets. 相似文献
8.
D.J.J. Farnell F.N. Hatfield M. Reakes D. Parry 《Journal of The Franklin Institute》2008,345(7):748-765
We employed multiscale line operators (MSLO) in order to segment blood vessels in digital fundus images. Separately, a median filter technique was used in order to provide results that were compared to those of the MSLO. The green channel of the colour image was used, and both sets of results were further enhanced by subsequently employing a simple “randomly seeded” region-growing algorithm. We applied this approach to two sets of retinal images, namely, the ARIA (www.eyecharity.com/aria_online/) and STARE (www.ces.clemson.edu/∼ahoover/stare/) retinal image archives. The ARIA dataset contained colour fundus images from healthy subjects, diabetic subjects, and age-related macular degeneration (AMD) subjects. Similarly, the STARE dataset contained images from both “normal” (i.e., healthy) and “abnormal” (i.e., diseased) eyes. Manual segmentations of the blood-vessel structure for all images in the ARIA and STARE datasets were obtained by a retinal image interpretation expert. These images were then taken to be our gold standards. Receiver-operator characteristic (ROC) curves were determined and the areas under the ROC curve (AZ) were obtained. A large increase in efficiency for our MSLO algorithm was observed for the entire datasets (ARIA AZ=0.899; STARE AZ=0.953) compared to basic thresholding alone (ARIA AZ=0.608; STARE AZ=0.753). Interestingly, the simple median filter algorithm followed by region growing also performed well (ARIA AZ=0.888; STARE AZ=0.947). Our results compared favourably to those results of previous segmentation procedures for the STARE dataset. As expected, the best results were found for the healthy control group for ARIA and for the normal subjects for STARE. 相似文献
9.
This study uses bibliometric analysis and citation context analysis to identify the influence of the main concepts embedded in Taylor’s 1968 classic article entitled Question-Negotiation and Information-Seeking in Libraries. This study analyses articles published between 1969 and 2010 which cite Taylor’s article. The results show that Taylor’s article on a question-negotiation model is increasingly visible and its influence is not limited to the discipline of library and information science. Of the 14 cited concepts identified, the concept of “four levels of information needs” was cited most (31.7%), followed by “question negotiation” (20.5%) and “other concepts relating to information needs” (17.9%). The results indicate an increasing trend in the citations of “four levels of information needs” and this concept also received the most attention from information retrieval research. A decreasing trend was evident for the concept of “question negotiation” and this concept was frequently cited by reference service researchers. In addition, among the 10 citation functions, “related literature” was dominant (30.8%). Both “evidence” and “views” were in second place with the same percentage (18.7%), followed by “terms” (9.2%) and “background information” (7.2%). A decreasing trend was identified in the top three citation functions, whereas an increasing trend was observed in the “term” and “background information” functions. 相似文献
10.
We review literatures that inform entrepreneurial innovation, paying particular attention to different conceptualizations of contexts. Early research explored micro and macro approaches with some scholars taking an actor-centric perspective and others a context-centric perspective. Bridging these perspectives, different scholars proposed multilevel approaches, arguing that opportunities are “found” or “made” by entrepreneurs whose efforts are moderated by contexts. More recent constitutive approaches, such as those informed by structuration, complexity and disequilibrium theories, have viewed entrepreneurial innovation as a process wherein actors and contexts are co-created. We add to constitutive approaches by examining how entrepreneurs contextualize innovation through narratives. A narrative perspective considers entrepreneurial innovation as an ongoing process involving embedded actors who contextualize innovation through performative efforts. We discuss the implications of this perspective for policy, entrepreneurs, and research. 相似文献
11.
This article describes in-depth research on machine learning methods for sentiment analysis of Czech social media. Whereas in English, Chinese, or Spanish this field has a long history and evaluation datasets for various domains are widely available, in the case of the Czech language no systematic research has yet been conducted. We tackle this issue and establish a common ground for further research by providing a large human-annotated Czech social media corpus. Furthermore, we evaluate state-of-the-art supervised machine learning methods for sentiment analysis. We explore different pre-processing techniques and employ various features and classifiers. We also experiment with five different feature selection algorithms and investigate the influence of named entity recognition and preprocessing on sentiment classification performance. Moreover, in addition to our newly created social media dataset, we also report results for other popular domains, such as movie and product reviews. We believe that this article will not only extend the current sentiment analysis research to another family of languages, but will also encourage competition, potentially leading to the production of high-end commercial solutions. 相似文献
12.
Bricolage versus breakthrough: distributed and embedded agency in technology entrepreneurship 总被引：2，自引：0，他引：2
We develop a perspective on technology entrepreneurship as involving agency that is distributed across different kinds of actors. Each actor becomes involved with a technology, and, in the process, generates inputs that result in the transformation of an emerging technological path. The steady accumulation of inputs to a technological path generates a momentum that enables and constrains the activities of distributed actors. In other words, agency is not only distributed, but it is embedded as well. We explicate this perspective through a comparative study of processes underlying the emergence of wind turbines in Denmark and in United States. Through our comparative study, we flesh out “bricolage” and “breakthrough” as contrasting approaches to the engagement of actors in shaping technological paths. 相似文献
13.
14.
Dirk Akkermans 《Research Policy》2009,38(1):181-191
In Varieties of Capitalism; The Institutional Foundations of Comparative Advantage, Peter A. Hall and David Soskice (H&S) argue that technological specialization patterns are largely determined by the prevailing “variety of capitalism”. They hypothesize that “liberal market economies” (LMEs) specialize in radical innovation, while “coordinated market economies” (CMEs) focus more on incremental innovation. Mark Zachary Taylor [Taylor, M.Z., 2004. Empirical evidence against varieties of capitalism's theory of technological innovation. International Organization 58, 601-631.] convincingly argued that Hall and Soskice's empirical test is fundamentally flawed and proposed a more appropriate test of their conjecture. He rejected the varieties of capitalism explanation of innovation patterns. We extend and refine Taylor's analysis, using a broader set of radicality indicators and making industry-level comparisons. Our results indicate that Hall and Soskice's conjecture cannot be upheld as a general rule, but that it survives closer scrutiny for a substantial number of industries and an important dimension of radicality. 相似文献
15.
Jerry Courvisanos 《Research Policy》2009,38(7):1117-1124
“Political aspects” that enhance, but also undermine, the positive transformational power of public innovation policies are examined. As such, this paper follows Micha? Kalecki in his 1943 paper that identifies the “political aspects” which enhance and undermine the positive transformational power of Keynesian full employment policies. Similarly, this paper provides a policy framework that identifies what government and business support as innovation policies. The role of innovation stems from Schumpeter's long-run perspective, but incorporates the more dynamic cyclical short-term and trend perspectives of Kalecki. This paper critiques the strategy of public innovation policy in general and derives policy implications. 相似文献
16.
《Information processing & management》2022,59(2):102842
The matrix factorization model based on user-item rating data has been widely studied and applied in recommender systems. However, data sparsity, the cold-start problem, and poor explainability have restricted its performance. Textual reviews usually contain rich information about items’ features and users’ sentiments and preferences, which can solve the problem of insufficient information from only user ratings. However, most recommendation algorithms that take sentiment analysis of review texts into account are either fine- or coarse-grained, but not both, leading to uncertain accuracy and comprehensiveness regarding user preference. This study proposes a deep learning recommendation model (i.e., DeepCGSR) that integrates textual review sentiments and the rating matrix. DeepCGSR uses the review sets of users and items as a corpus to perform cross-grained sentiment analysis by combining fine- and coarse-grained levels to extract sentiment feature vectors for users and items. Deep learning technology is used to map between the extracted feature vector and latent factor through the rating-based matrix factorization model and obtain deep, nonlinear features to predict the user's rating of an item. Iterative experiments on e-commerce datasets from Amazon show that DeepCGSR consistently outperforms the recommendation models LFM, SVD++, DeepCoNN, TOPICMF, and NARRE. Overall, comparing with other recommendation models, the DeepCGSR model demonstrated improved evaluation results by 14.113% over LFM, 13.786% over SVD++, 9.920% over TOPICMF, 5.122% over DeepCoNN, and 2.765% over NARRE. Meanwhile, the DeepCGSR has great potential in fixing the overfitting and cold-start problems. Built upon previous studies and findings, the DeepCGSR is the state of the art, moving the design and development of the recommendation algorithms forward with improved recommendation accuracy. 相似文献
17.
Richard R. Nelson 《Research Policy》2008,37(1):1-11
In recent years “institutions” have again become a central focus of economists and other scholars studying the processes of economic growth, and the reasons why nations have differed so greatly in their achievements on this front. However, with few exceptions the exploration of the role of institutions has not been connected with a coherent analysis of the relationships between institutions and institutional change and technological advance. This paper proposes a way of analyzing these relationships. The concept of “social technologies” which support “physical technologies” plays a key role in the analysis. 相似文献
18.
《Information processing & management》2022,59(5):103038
As an emerging task in opinion mining, End-to-End Multimodal Aspect-Based Sentiment Analysis (MABSA) aims to extract all the aspect-sentiment pairs mentioned in a pair of sentence and image. Most existing methods of MABSA do not explicitly incorporate aspect and sentiment information in their textual and visual representations and fail to consider the different contributions of visual representations to each word or aspect in the text. To tackle these limitations, we propose a multi-task learning framework named Cross-Modal Multitask Transformer (CMMT), which incorporates two auxiliary tasks to learn the aspect/sentiment-aware intra-modal representations and introduces a Text-Guided Cross-Modal Interaction Module to dynamically control the contributions of the visual information to the representation of each word in the inter-modal interaction. Experimental results demonstrate that CMMT consistently outperforms the state-of-the-art approach JML by 3.1, 3.3, and 4.1 absolute percentage points on three Twitter datasets for the End-to-End MABSA task, respectively. Moreover, further analysis shows that CMMT is superior to comparison systems in both aspect extraction (AE) and sentiment classification (SC), which would move the development of multimodal AE and SC algorithms forward with improved performance. 相似文献
19.
《Information processing & management》2023,60(2):103223
Aspect-based sentiment analysis aims to determine sentiment polarities toward specific aspect terms within the same sentence or document. Most recent studies adopted attention-based neural network models to implicitly connect aspect terms with context words. However, these studies were limited by insufficient interaction between aspect terms and opinion words, leading to poor performance on robustness test sets. In addition, we have found that robustness test sets create new sentences that interfere with the original information of a sentence, which often makes the text too long and leads to the problem of long-distance dependence. Simultaneously, these new sentences produce more non-target aspect terms, misleading the model because of the lack of relevant knowledge guidance. This study proposes a knowledge guided multi-granularity graph convolutional neural network (KMGCN) to solve these problems. The multi-granularity attention mechanism is designed to enhance the interaction between aspect terms and opinion words. To address the long-distance dependence, KMGCN uses a graph convolutional network that relies on a semantic map based on fine-tuning pre-trained models. In particular, KMGCN uses a mask mechanism guided by conceptual knowledge to encounter more aspect terms (including target and non-target aspect terms). Experiments are conducted on 12 SemEval-2014 variant benchmarking datasets, and the results demonstrated the effectiveness of the proposed framework. 相似文献
20.
Many authors have proposed categorizations for approaches to Knowledge Management; outstanding prospects including functionalist and interpretativist. In the first approach, knowledge is considered as a “static object” that exists in a number of ways and locations; in the second one, knowledge does not exist independently of human experience, social practice, of knowledge itself and its use, where it is shared by the social practices of communities, because it is “dynamic and active”. These articles constitute an extensive review on the subject, focused in reviewing, analyzing and presenting a study of the interpretativist perspective, and describe a maturity model for KM operational from it. 相似文献