A frequent goal of a researcher is to publish his/her work in appropriate conferences and journals. With a large number of options for venues in the microdomains of every research discipline, the issue of selecting suitable locations for publishing cannot be underestimated. Further, the venues diversify themselves in the form of workshops, symposiums, and challenges. Several publishers such as IEEE and Springer have recognized the need to address this issue and have developed journal recommenders. In this thesis, our goal is to design and develop a similar recommendation system for the ACM dataset. We view this recommendation problem from a classification perspective. With the success of deep learning classifiers in recent times and their pervasiveness in several domains, we modeled several 1D Convolutional neural network classifiers for the different venues. When given some submission information like title, keywords, abstract, etc. about a paper, the recommender uses these developed classifier predictions to recommend suitable venues to the user. The dataset used for the project is the ACM Digital Library metadata that includes textual information for research papers and journals submitted at various conferences and journals over the past 60 years. We developed the recommender based on two approaches: 1) A binary CNN classifier per venue (single classifiers), and 2) Group CNN classifiers for venue groups (group classifiers). Our system has achieved a MAP of 0.55 and 0.51 for single and group classifiers. We also show that our system has a high recall rate. / Master of Science / A frequent goal of a researcher is to publish his/her research work in the form of papers and journals at recognized publication conferences and journals. Conferences limit the number of pages in a submission, whereas journals tend to be flexible with the length. In general, academic conferences are held annually, while journals have a submission cut off date on a monthly/trimonthly or so basis. These conferences and journals are publication venues. With a large number of options for venues in the microdomains of every research discipline, the issue of selecting suitable locations for publishing is a complicated task. Further, the venues diversify themselves in the form of workshops, symposiums, and challenges. Submitting a work to the wrong venue often leads to a rejection. Every author who is about to publish faces this question of ``Where can I publish my work so that it gets accepted?". This thesis is an attempt to address this question through a recommendation system. Recommendation systems help us in the decision making process. A well-known example is the ``Customers who bought this also bought item y'' message we find in eCommerce websites. These systems help users navigate a product catalog better to address their needs. The goal of this thesis is to develop one such recommendation system that can help researchers to choose venues. When an author is about to publish, they structure their paper/journal in the form of a research title, brief abstract, relevant keywords in the paper, and a detailed explanation of the research carried out. Our system can take any of these as input and suggest appropriate venues based on the submission content. The dataset used for the project is the ACM Digital Library metadata. We developed the recommender using deep learning techniques. Our system can be helpful for finding a single best venue, or a group of suitable venues.

The ISI provides librarians with tools such as the Journal Citation Reports (JCR) and the institution specific Local Journal Utilization Report (LJUR) to aid in the management of serials collections. These tools enable librarians to respond quickly to changes in publishing practices and purchasing options. While available literature often criticizes ISI data, few studies provide concrete recommendations for improvement. This study explores two extensions to LJUR: (1) adding citation date and (2) creating institution specific impact factors. In addition, I explore the degree to which self-citations influence the ISI impact factor. Publication and citation calculations are made for three prominent southern universities’ research chemists using a corpus of full text articles drawn from 27 American Chemical Society (ACS) journals and stored in an Oracle database. The ACS research corpus impact factor simulation and ACS research corpus self-citation omission impact factor are also created and compared with current JCR data.

Die Aufgabe, ein passendes Journal zu finden, ist auf Grund von verschiedenen Einschränkungen nicht von Hand zu erledigen. Um also diese Problematik zu behandeln, entwickelt die aktuelle Untersuchung ein Journal-Empfehlungssystem, das – in einer Komponente – die inhaltlichen Ähnlichkeiten zwischen einem Manuskript und den existierenden Zeitschriftenartikeln in einem Korpus vergleicht. Das stellt die inhaltsbasierte Empfehlungskomponente des Systems dar. Zusätzlich beinhaltet das System eine wissensbasierte Empfehlungskomponente, um die Anforderungen des Autors bezüglich der Veröffentlichung auf Basis von 15 Journal-Auswahlkriterien zu berücksichtigen. Das neue System gibt Empfehlungen aus den im Directory of Open Access Journals indizierten Journals für zwei verschiedene Themengebiete: Medizin und Sozialwissenschaften. Die Ergebnisse zeigen, dass die Autoren aus den Themengebieten Medizin und Sozialwissenschaften mit den Empfehlungen des Systems zu 66,2% bzw. 58,8% einverstanden waren. Darüber hinaus wurde 35,5% der Autoren aus dem Bereich Medizin und 40,4% der Autoren aus den Sozialwissenschaften ein oder mehrere Journal(s) vorgeschlagen, das bzw. die für die Publikation besser geeignet war(en) als das Journal, in dem sie den Artikel veröffentlich hatten. Die durchschnittliche Leistung des Systems zeigte eine Abnahme von 15% in Medizin bzw. 18% in Sozialwissenschaften verglichen mit den gleichen Empfehlungen bei einer optimalen Sortierung. Leistungsverluste von 22,4% im Fach Medizin und 28,4% in den Sozialwissenschaften ergaben sich, wenn die durchschnittliche Leistung mit einem System verglichen wurde, das geeignete Empfehlungen für die 10 besten Resultate in der optimalen Reihenfolge sortiert abruft. Die vom Hybrid-Modell Empfehlungen zeigen zwar eine etwas bessere Leistung als die inhaltsbasierte Komponente, die Verbesserung war aber nicht statistisch signifikant. / The task of finding appropriate journals cannot be accomplished manually due to a number of limitations of the approach. Therefore, to address this issue, the current research develops a journal recommender system with two components: the first component compares the content similarities between a manuscript and the existing journal articles in a corpus. This represents the content-based recommender component of the system. In addition, the system includes a knowledge-based recommender component to consider authors’ publication requirements based on 15 journal selection factors. The new system makes recommendations from the open access journals indexed in the directory of open access journals for two distinct subject domains, namely medicine and social sciences. The results indicated that the authors from medicine and social sciences agree with the recommender’s suggestions by 66.2% and 58.8% respectively. Moreover, 35.5% of medicine and 40.4% of social sciences authors were suggested more appropriate journal(s) than the journal they already published in. Average performance of the system demonstrated 15% and 18% performance loss in medicine and social sciences respectively against the same suggestions after arranging according to the most appropriate order. Numbers were reported as 22.4% and 28.4% of loss in medicine and social sciences respectively when the average performance was compared with a system that retrieves appropriate suggestions for all 10 topmost results according to the most appropriate order. Although the hybrid recommender demonstrated a slight advancement of performance than the content-based component, the improvement was not statistically significant.