科研社交網(wǎng)站中的學(xué)者推薦研究
發(fā)布時(shí)間：2018-11-08 16:26
【摘要】：Web2.0時(shí)代,社交網(wǎng)絡(luò)用戶可以自由的發(fā)布信息、交流思想,吸引了人們?cè)谠擃惼脚_(tái)上建立社區(qū)、交流知識(shí),由于一般社交網(wǎng)絡(luò)缺乏專業(yè)學(xué)術(shù)氛圍,2007年起出現(xiàn)了專門面向?qū)W術(shù)工作者的科研社交網(wǎng)站,如國(guó)外的ResearchGate、Academia.edu,國(guó)內(nèi)的百度學(xué)術(shù)、科研之友等。他們?cè)诰W(wǎng)站中瀏覽彼此主頁(yè)、尋找感興趣的文獻(xiàn)與學(xué)者、參與學(xué)術(shù)話題討論、相互提問解答,這使得全球各領(lǐng)域科研人員能夠方便地進(jìn)行即時(shí)學(xué)術(shù)探討、尋求潛在合作機(jī)會(huì)。發(fā)現(xiàn)相似研究學(xué)者與潛在合作者是科研工作者使用網(wǎng)站的重要理由之一。但是,科研社交網(wǎng)絡(luò)存在與大眾社交網(wǎng)絡(luò)相同的信息過載、信息不對(duì)稱的問題,基于學(xué)者的學(xué)術(shù)知識(shí)與科研合作網(wǎng)絡(luò)構(gòu)建個(gè)性化推薦模型是有效的解決手段。進(jìn)一步地,目前信息處理與檢索系統(tǒng)的一個(gè)新趨勢(shì)是對(duì)情境化數(shù)據(jù)的獲取,將其考慮進(jìn)信息處理中,有助于提高推薦精確度,緩解信息過載,更好的適應(yīng)與用戶已有歷史記錄相獨(dú)立的特殊需求。為此,本文分析了科研社交網(wǎng)站中學(xué)者的社交動(dòng)機(jī),得出推薦場(chǎng)景差異,認(rèn)為學(xué)者主要對(duì)同一研究領(lǐng)域、具有相似研究偏好的學(xué)者感興趣,并與他們建立長(zhǎng)期的社交關(guān)系,除此外,很多學(xué)者具有情境化特征,希望尋找具有特定要求限制下的合作者,如已有研究主題的項(xiàng)目或者論文。因此,本文提出了兩個(gè)學(xué)者推薦模型,即基于相似研究興趣的學(xué)者推薦模型,和基于特定情境的合作者推薦模型。針對(duì)兩種推薦情境,本文分別設(shè)計(jì)了合理對(duì)應(yīng)的解決策略。在基于相似研究興趣的學(xué)者推薦模型中,本文構(gòu)造了兩個(gè)子模型:學(xué)者檔案模型與學(xué)術(shù)行為網(wǎng)絡(luò)模型。在學(xué)者檔案模型中,采用語言模型,依據(jù)學(xué)者的專業(yè)、研究領(lǐng)域、研究成果等信息表征學(xué)者知識(shí),使用基于貝葉斯分解的生成概率計(jì)算學(xué)者知識(shí)的相似度;在學(xué)術(shù)行為網(wǎng)絡(luò)模型中,通過挖掘?qū)W者學(xué)術(shù)行為網(wǎng)絡(luò)中的關(guān)系,采用Adamic-Adar方法和最短路徑方法分別測(cè)量合作者網(wǎng)絡(luò)中的學(xué)者節(jié)點(diǎn)相似度和路徑距離,從全局學(xué)術(shù)領(lǐng)域和局部研究領(lǐng)域兩個(gè)角度采用Jaccard系數(shù)表示研究學(xué)者所在單位間的合作網(wǎng)絡(luò)關(guān)系度;最后,應(yīng)用Comb策略整合以上測(cè)量,預(yù)測(cè)相似度較高的學(xué)者為推薦學(xué)者。在基于特定情境下的合作者推薦模型中,本文設(shè)計(jì)了兩個(gè)標(biāo)準(zhǔn)評(píng)定潛在合作者的質(zhì)量:學(xué)者學(xué)術(shù)質(zhì)量評(píng)價(jià)與學(xué)術(shù)社會(huì)網(wǎng)絡(luò)質(zhì)量評(píng)價(jià)。在學(xué)者學(xué)術(shù)質(zhì)量評(píng)價(jià)中,同時(shí)引入情境預(yù)過濾和情境后過濾到推薦方法中,使用學(xué)者的學(xué)術(shù)成果質(zhì)量(成果數(shù)量、發(fā)表刊物級(jí)別、被引用量)、職稱、G指數(shù)來為學(xué)者的學(xué)術(shù)能力評(píng)分,對(duì)情境信息進(jìn)行預(yù)處理、提取特征詞,首先采用情境預(yù)過濾策略選出含有情境內(nèi)容特征的學(xué)者構(gòu)成初步候選合作者集,然后采用調(diào)整的潛狄利克雷分配方法對(duì)情景主題分配關(guān)鍵詞,運(yùn)用Kullback-Leibler差異計(jì)算初步候選合作者集中的學(xué)者與目標(biāo)學(xué)者間的知識(shí)匹配,并將MNZ標(biāo)準(zhǔn)化后的學(xué)者學(xué)術(shù)能力評(píng)分作為匹配計(jì)算中的權(quán)重值;在學(xué)術(shù)社會(huì)網(wǎng)絡(luò)質(zhì)量評(píng)價(jià)中,構(gòu)建了多元關(guān)系網(wǎng)絡(luò),包括四種關(guān)系類型:論文合作、項(xiàng)目合作、專利合作、出席相同會(huì)議,先計(jì)算學(xué)者間四種關(guān)系的數(shù)量,再引入關(guān)系年限修正得到合作質(zhì)量評(píng)分;最后對(duì)兩項(xiàng)評(píng)分進(jìn)行整合得到合作意向評(píng)分。兩個(gè)推薦模型的具體構(gòu)建方法見于論文第四章。同時(shí),為了模型應(yīng)用的清晰與完整性,本文構(gòu)建了科研社交網(wǎng)絡(luò)的全局系統(tǒng)架構(gòu),并采用Python2.7+Selenium+Scrapy搭建爬蟲,得到2000名學(xué)者作為模型模擬數(shù)據(jù)集,收集到共8萬多項(xiàng)學(xué)術(shù)成果,本文在第五章中詳細(xì)給出了模型的應(yīng)用過程與每一步驟的計(jì)算值,實(shí)驗(yàn)結(jié)果表明,模型具有應(yīng)用可行性和較好的推薦效果。
[Abstract]:In the Web 2.0 era, social network users can freely distribute information and exchange ideas, and attract people to build community and exchange knowledge on such platforms. As a result of the lack of professional academic atmosphere in the general social network, social networking sites for academic workers have emerged in 2007. such as the foreign research group, the Academia.edu, the domestic Baidu academic, the scientific research friends and so on. They visit each other's home page in the website, find the literature and scholars of interest, participate in the discussion of the academic topic, and ask each other to answer the questions, which makes the researchers in all fields of the world can carry on the real-time academic discussion and seek the potential cooperation opportunity. It is found that similar research scholars and potential collaborators are one of the important reasons for scientific research workers to use the website. However, the social network of scientific research has the same information overload and information asymmetry with the public social network, and it is an effective solution to construct the personalized recommendation model based on the academic knowledge of the scholars and the scientific research cooperation network. Further, a new trend of the present information processing and retrieval system is to obtain the contextual data, to take into account the information processing, to improve the recommended accuracy, to alleviate the overload of the information, and to better adapt to the special needs independent of the user's existing history. To this end, this paper analyzes the social motivation of the scholars in the social network of scientific research, and draws the difference of the recommended scene, and thinks that the scholars are interested in the same research field and have similar research and preference, and establish a long-term social relationship with them, and, in addition, Many of the scholars have a contextual feature, looking for collaborators with specific requirements, such as projects or papers with research topics. In this paper, two academic recommendation models, namely, a recommendation model based on similar research interests, and a co-author recommendation model based on a specific context, are proposed in this paper. In this paper, a reasonable and corresponding solution is designed for two recommended situations. In the author's recommendation model based on similar research interest, the paper constructs two sub-models: the academic file model and the academic behavior network model. in that scholar's file model, the language model is adopted, and the knowledge of the scholar is characterized by the information of the professional, the research field, the research result and the like of the scholar, and the similarity of the knowledge of the scholar is calculated by using the generation probability based on the Bayesian decomposition; in the network model of the academic behavior, by digging the relationship between the scholar's academic behavior network, the Adamic-Adar method and the shortest path method are adopted to measure the similarity and the path distance of the scholar nodes in the partner network, From the global academic field and the local research field, the Jaccard coefficient is used to show the relationship degree of the cooperative network between the research scholars and the research scholars. Finally, the author uses the Comb strategy to integrate the above measurement, and the scholars with higher similarity are predicted to be the recommended scholars. In the model of co-author's recommendation based on the specific situation, this paper designs two criteria to evaluate the quality of potential collaborators: the evaluation of the academic quality and the evaluation of the network quality of the academic society. in that evaluation of the academic quality of the scholar, the situation pre-filtration and the situation are introduced into the recommendation method, the academic achievement quality (the number of achievement, the publication level, the quoted amount), the professional title and the G index of the scholar are used to score the academic ability of the scholar, pre-processing the situation information, extracting the characteristic words, first adopting a context pre-filtering strategy to select a first candidate partner set containing the context content feature, and then using the adjusted latent Dirichlet distribution method to assign a keyword to the scene theme, using the Kullback-Leibler difference to calculate the knowledge matching between the scholars and the target scholars in the preliminary candidate collaborator, and the academic ability score of the scholars after the MNZ standardization is used as the weight value in the matching calculation; in the network quality evaluation of the academic society, a multi-element relationship network is constructed, It includes four types of relationship: paper cooperation, project cooperation, patent cooperation, attendance at the same meeting, first calculating the number of four relationships among the scholars, and then introducing the relationship life correction to obtain the cooperation quality score; and finally, combining the two scores to obtain the cooperation intention score. The specific construction methods of two recommended models are found in the fourth chapter of the thesis. At the same time, for the sake of clarity and completeness of the model application, this paper constructs the global system architecture of the scientific research social network, and sets up the crawler by Python2.7 + Selenium + Srapy, and obtains 2000 scholars as the model model data set, and collects over 80,000 academic achievements. In the fifth chapter, the application process of the model and the calculation value of each step are given in detail. The experimental results show that the model has the application feasibility and the better recommended effect.
【學(xué)位授予單位】：華中師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP393.092;G354
本文編號(hào)：2319034
[Abstract]:In the Web 2.0 era, social network users can freely distribute information and exchange ideas, and attract people to build community and exchange knowledge on such platforms. As a result of the lack of professional academic atmosphere in the general social network, social networking sites for academic workers have emerged in 2007. such as the foreign research group, the Academia.edu, the domestic Baidu academic, the scientific research friends and so on. They visit each other's home page in the website, find the literature and scholars of interest, participate in the discussion of the academic topic, and ask each other to answer the questions, which makes the researchers in all fields of the world can carry on the real-time academic discussion and seek the potential cooperation opportunity. It is found that similar research scholars and potential collaborators are one of the important reasons for scientific research workers to use the website. However, the social network of scientific research has the same information overload and information asymmetry with the public social network, and it is an effective solution to construct the personalized recommendation model based on the academic knowledge of the scholars and the scientific research cooperation network. Further, a new trend of the present information processing and retrieval system is to obtain the contextual data, to take into account the information processing, to improve the recommended accuracy, to alleviate the overload of the information, and to better adapt to the special needs independent of the user's existing history. To this end, this paper analyzes the social motivation of the scholars in the social network of scientific research, and draws the difference of the recommended scene, and thinks that the scholars are interested in the same research field and have similar research and preference, and establish a long-term social relationship with them, and, in addition, Many of the scholars have a contextual feature, looking for collaborators with specific requirements, such as projects or papers with research topics. In this paper, two academic recommendation models, namely, a recommendation model based on similar research interests, and a co-author recommendation model based on a specific context, are proposed in this paper. In this paper, a reasonable and corresponding solution is designed for two recommended situations. In the author's recommendation model based on similar research interest, the paper constructs two sub-models: the academic file model and the academic behavior network model. in that scholar's file model, the language model is adopted, and the knowledge of the scholar is characterized by the information of the professional, the research field, the research result and the like of the scholar, and the similarity of the knowledge of the scholar is calculated by using the generation probability based on the Bayesian decomposition; in the network model of the academic behavior, by digging the relationship between the scholar's academic behavior network, the Adamic-Adar method and the shortest path method are adopted to measure the similarity and the path distance of the scholar nodes in the partner network, From the global academic field and the local research field, the Jaccard coefficient is used to show the relationship degree of the cooperative network between the research scholars and the research scholars. Finally, the author uses the Comb strategy to integrate the above measurement, and the scholars with higher similarity are predicted to be the recommended scholars. In the model of co-author's recommendation based on the specific situation, this paper designs two criteria to evaluate the quality of potential collaborators: the evaluation of the academic quality and the evaluation of the network quality of the academic society. in that evaluation of the academic quality of the scholar, the situation pre-filtration and the situation are introduced into the recommendation method, the academic achievement quality (the number of achievement, the publication level, the quoted amount), the professional title and the G index of the scholar are used to score the academic ability of the scholar, pre-processing the situation information, extracting the characteristic words, first adopting a context pre-filtering strategy to select a first candidate partner set containing the context content feature, and then using the adjusted latent Dirichlet distribution method to assign a keyword to the scene theme, using the Kullback-Leibler difference to calculate the knowledge matching between the scholars and the target scholars in the preliminary candidate collaborator, and the academic ability score of the scholars after the MNZ standardization is used as the weight value in the matching calculation; in the network quality evaluation of the academic society, a multi-element relationship network is constructed, It includes four types of relationship: paper cooperation, project cooperation, patent cooperation, attendance at the same meeting, first calculating the number of four relationships among the scholars, and then introducing the relationship life correction to obtain the cooperation quality score; and finally, combining the two scores to obtain the cooperation intention score. The specific construction methods of two recommended models are found in the fourth chapter of the thesis. At the same time, for the sake of clarity and completeness of the model application, this paper constructs the global system architecture of the scientific research social network, and sets up the crawler by Python2.7 + Selenium + Srapy, and obtains 2000 scholars as the model model data set, and collects over 80,000 academic achievements. In the fifth chapter, the application process of the model and the calculation value of each step are given in detail. The experimental results show that the model has the application feasibility and the better recommended effect.
【學(xué)位授予單位】：華中師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP393.092;G354
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 胡文靜;王睿;;社交網(wǎng)絡(luò)學(xué)術(shù)活動(dòng)特征分析及應(yīng)對(duì)策略[J];情報(bào)資料工作;2017年01期
2 趙楊;李露琪;;國(guó)內(nèi)外學(xué)術(shù)社交網(wǎng)絡(luò)研究現(xiàn)狀述評(píng)與思考[J];情報(bào)資料工作;2016年06期
3 吳燎原;蔣軍;王剛;;科研社交網(wǎng)絡(luò)中基于聯(lián)合概率矩陣分解的科技論文推薦方法研究[J];計(jì)算機(jī)科學(xué);2016年09期
4 王曰芬;賈新露;傅柱;;學(xué)術(shù)社交網(wǎng)絡(luò)用戶內(nèi)容使用行為研究——基于科學(xué)網(wǎng)熱門博文的實(shí)證分析[J];現(xiàn)代圖書情報(bào)技術(shù);2016年06期
5 黃泳航;湯庸;李春英;湯志康;劉繼偉;;基于社區(qū)劃分的學(xué)術(shù)論文推薦模型[J];計(jì)算機(jī)應(yīng)用;2016年05期
6 賈新露;王曰芬;;學(xué)術(shù)社交網(wǎng)絡(luò)的概念、特點(diǎn)及研究熱點(diǎn)[J];圖書館學(xué)研究;2016年05期
7 陳明紅;漆賢軍;劉瑩;;科研社交網(wǎng)絡(luò)使用行為的影響因素研究[J];情報(bào)理論與實(shí)踐;2015年10期
8 段慶鋒;;我國(guó)科研人員在線學(xué)術(shù)社交模式實(shí)證研究:以科學(xué)網(wǎng)為例[J];情報(bào)雜志;2015年09期
9 李春英;湯庸;湯志康;黃泳航;袁成哲;趙劍冬;;面向大規(guī)模學(xué)術(shù)社交網(wǎng)絡(luò)的社區(qū)發(fā)現(xiàn)模型[J];計(jì)算機(jī)應(yīng)用;2015年09期
10 袁成哲;曾碧卿;湯庸;王大豪;曾惠敏;;面向?qū)W術(shù)社交網(wǎng)絡(luò)的多維度團(tuán)隊(duì)推薦模型[J];計(jì)算機(jī)科學(xué)與探索;2016年02期
相關(guān)博士學(xué)位論文 前2條
1 楊辰;科研社交網(wǎng)絡(luò)平臺(tái)中的合作者推薦[D];中國(guó)科學(xué)技術(shù)大學(xué);2015年
2 孫見山;科研社交網(wǎng)絡(luò)中的論文推薦[D];中國(guó)科學(xué)技術(shù)大學(xué);2014年
相關(guān)碩士學(xué)位論文 前1條
1 趙蒙;知識(shí)學(xué)習(xí)社交網(wǎng)絡(luò)的研究與實(shí)現(xiàn)[D];北京郵電大學(xué);2014年
，本文編號(hào)：2319034
本文鏈接：http://sikaile.net/tushudanganlunwen/2319034.html
最近更新
教材專著
