2,268 research outputs found
Guidelines for Developing Bots for GitHub
No full textProjects on GitHub rely on the automation provided by software development bots. Nevertheless, the presence of bots can be annoying and disruptive to the community. Backed by multiple studies with practitioners, this article provides guidelines for developing and maintaining software bots.Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Software Engineerin
Human Aided Bots
No full textA chatbot is an example of a text-based conversational agent. While natural language understanding and machine learning techniques advance rapidly, current fully automated chatbots still struggle to serve their users well. Human intelligence, brought by crowd workers, freelancers or even full-time employees can be embodied in the chatbot logic to fill the gaps caused by limitations of fully automated solutions. In this paper we investigate Human Aided Bots, i.e. bots (including chatbots) using humans in the loop to operate. We survey industrial and academic examples of human aided bots, discuss their differences and common patterns, and identify open research questions.Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Web Information System
Types of Bots: Categorization of Accounts Using Unsupervised Machine Learning
No full textabstract: Social media bot detection has been a signature challenge in recent years in online social networks. Many scholars agree that the bot detection problem has become an "arms race" between malicious actors, who seek to create bots to influence opinion on these networks, and the social media platforms to remove these accounts. Despite this acknowledged issue, bot presence continues to remain on social media networks. So, it has now become necessary to monitor different bots over time to identify changes in their activities or domain. Since monitoring individual accounts is not feasible, because the bots may get suspended or deleted, bots should be observed in smaller groups, based on their characteristics, as types. Yet, most of the existing research on social media bot detection is focused on labeling bot accounts by only distinguishing them from human accounts and may ignore differences between individual bot accounts. The consideration of these bots' types may be the best solution for researchers and social media companies alike as it is in both of their best interests to study these types separately. However, up until this point, bot categorization has only been theorized or done manually. Thus, the goal of this research is to automate this process of grouping bots by their respective types. To accomplish this goal, the author experimentally demonstrates that it is possible to use unsupervised machine learning to categorize bots into types based on the proposed typology by creating an aggregated dataset, subsequent to determining that the accounts within are bots, and utilizing an existing typology for bots. Having the ability to differentiate between types of bots automatically will allow social media experts to analyze bot activity, from a new perspective, on a more granular level. This way, researchers can identify patterns related to a given bot type's behaviors over time and determine if certain detection methods are more viable for that type.Dissertation/ThesisPresentation Materials for Thesis DefenseMasters Thesis Computer Science 201
Characterizing Social Bots Spreading Financial Disinformation
No full textDespite the existence of several studies on the characteristics and role of social bots in spreading disinformation related to politics, health, science and education, financial social bots remain a largely unexplored topic. We aim to shed light on this issue by investigating the activities of large social botnets in Twitter, involved in discussions about stocks traded in the main US financial markets. We show that the largest discussion spikes are in fact caused by mass-retweeting bots. Then, we focus on characterizing the activity of these financial bots, finding that they are involved in speculative campaigns aimed at promoting low-value stocks by exploiting the popularity of high-value ones. We conclude by highlighting the peculiar features of these accounts, comprising similar account creation dates, similar screen names, biographies, and profile pictures. These accounts appear as untrustworthy and quite simplistic bots, likely aiming to fool automatic trading algorithms rather than human investors. Our findings pave the way for the development of accurate detection and filtering techniques for financial spam. In order to foster research and experimentation on this novel topic, we make our dataset publicly available for research purposes
Survey of political bots on Twitter
No full textBots are software applications that execute automated tasks called scripts over the Internet. Bots have become predominant on social media platforms like Twitter, and automate their interactions with other users. Political Twitter bots have emerged that focus their activity on elections, policy issues, and political crises. These political bots have faced increased scrutiny as a result of their association with online manipulation via the spread of misinformation. As bots have become more sophisticated, research has focused on advanced methods to detect their presence on social media platforms. However, little research has been performed on the overall presence of political bots and their dynamic response to political events. The research that has been performed on political bots focuses on these bots in the context of scheduled political events, such as elections. In this paper, we explore the bot response to an unexpected political event, describe the overall presence of political bots on Twitter, and design and employ a model to identify them based on their user profile alone. We collected data for more than 700,000 accounts tweeting with hashtags related to political events in the United States between May 2018 and October 2018. We designed a machine learning algorithm using user profile features alone that achieves approximately 97.4% accuracy in identifying political Twitter bots. In our analysis, we found (1) new bot accounts are created in response to political events, (2) bot accounts are more active during political controversies, (3) the number of tweets an account has favorited (liked) is a strong determinant of bot status.M.S.Includes bibliographical referencesby David Troup
Product searching with shopping bots
No full textShopping bots are an important new innovation which support consumers with the product search and identification stage in e-shopping. This paper reviews the search facilities offered by shopping bots. A number of shopping bots that include books in their product range, have been visited with a view to analysing their search facilities. Using trial searches for three different best-selling books, title, author, and keyword search facilities available in a number of bots were further investigated. Finally the output from the search in terms of the number of items, and suppliers identified, and the price, was analysed. The effectiveness of bots does not only depend upon search facilities but also depends upon product coverage, and other added value features such as publisher and consumer reviews. Consumer search behaviour, in general, and the way in which consumers will use shopping bots are fruitful areas for further research
Categorizing and Discovering Social Bots
No full textabstract: Bots tamper with social media networks by artificially inflating the popularity of certain topics. In this paper, we define what a bot is, we detail different motivations for bots, we describe previous work in bot detection and observation, and then we perform bot detection of our own. For our bot detection, we are interested in bots on Twitter that tweet Arabic extremist-like phrases. A testing dataset is collected using the honeypot method, and five different heuristics are measured for their effectiveness in detecting bots. The model underperformed, but we have laid the ground-work for a vastly untapped focus on bot detection: extremist ideal diffusion through bots
Software Bots in Software Engineering: Benefits and Challenges
No full textSoftware bots are becoming increasingly popular in software engineering (SE). In this tutorial, we define what a bot is and present several examples. We also discuss the many benefits bots provide to the SE community, including helping in development tasks (such as pull request review and integration) and onboarding newcomers to a project. Finally, we discuss the challenges related to interacting with and developing software bots.Software Engineerin
HR bots in human resource management of an organization
No full textThe article analyzes a relatively new phenomenon of the digital economy — HR bots. Th e author
outlines that in scientifi c literature there is no clear definition what HR bots are, what are their
specifi c features are, and what their impact on the effectiveness of human resource management
is. Th e objectives of the article are to defi ne the concept of an “HR bot”, identify its types and
functions in the human resource management, and consider the challenges that HR departments
face regarding the implementation of HR bots. Th e article consists of three sections. In the first
section the author discusses a more general concept of a “bot”, describes the type and directions
of using bots. The second section relates to a detailed consideration of HR bots, their types and
functions in human resource management. In the third section basing on the research available
in the fi eld and experts’ opinion the author characterizes HR bots’ capabilities in improving the
effi ciency of human resource management and the challenges that HR departments face when
implementing HR bots. The key findings of the article are: the concept of an HR bot is clarified;
the typology of HR bots is carried out; the scope of HR bot application is systematized, as well as
their strengths and weaknesses, and prospects for further research in the field are identified. The
article systematizes the diverse knowledge on bots and HR bots, therefore it can be useful both to
researchers and practitioners in the field of human resource management.The article is written in framework of the project “The structure of the botnet space of social networks:
network analysis” supported by the Russian Foundation for Basic Research. Project No. 18-011-00988
On Communication Assistance Via Bots —Towards IMDJ
No full textAbstractCommunication robots (bots) have been popular in our lives. Actually robots have several shapes and possibilities. In several applications such as SNS, bots with simple pattern matching are installed and they do not provide natural conversation. However users sometimes can enjoy the conversation. There might be a certain shikake in the applications or users can enjoy the vertual conversation as it is.In this paper we investigate what types of bot are preferable in the Human-Computer interaction. We prepare several types of bot to determine the preferable features of bots. From the experiments, we could determine types of words for an enjoyable or comfortable conversation (interaction). Thus we can install such a conversation shikake in the bot applications. In addition, we will give a certain suggestion for the preparation of a certain mechanism for the conversation activation in the Innovators Marketplace on Data Jacket (IMDJ)
- …
