000 Informatik, Informationswissenschaft, allgemeine Werke
Refine
Document Type
- Article (1)
- Part of a Book (1)
- Conference Proceeding (1)
- Doctoral Thesis (1)
Institute
Language
- English (4) (remove)
Has Fulltext
- yes (4)
Is part of the Bibliography
- yes (4)
Keywords
Empirical insights into promising commercial sentiment analysis solutions that go beyond the claims of their vendors are rare. Moreover, due to the constant evolution in the field, previous studies are far from reflecting the current situation. The goal of this article is to evaluate and compare current solutions using two experimental studies. In the first part of the study, based on tweets about airline service quality, we test the solutions of six vendors with different market power, such as Amazon, Google, IBM, Microsoft, Lexalytics, and MeaningCloud, and report their measures of accuracy, precision, recall, (macro)F1, time performance, and service level agreements (SLA). Furthermore, we compare two of the services in depth with multiple data sets and over time. The services tested here are Google Cloud Natural Language API and MeaningCloud Sentiment Analysis API. For evaluating the results over time, we use the same data set as in November 2020. In addition, further topic-specific and general Twitter data sets are used. The experiments show that the IBM Watson NLU and Google Cloud Natural Language API solutions may be preferred when negative text detection is the primary concern. When tested in July 2022, the Google Cloud Natural Language API was still the clear winner compared to the MeaningCloud Sentiment Analysis API, but only on the airline service quality data set; on the other data sets, both services provided specific benefits and drawbacks. Furthermore, we detected changes in the sentiment classification over time with both services. Our results motivate that an independent, critical, and longitudinal experimental analysis of sentiment analysis services can provide interesting insights into their overall reliability and particular classification accuracy beyond marketing claims to critically compare solutions based on real data and analyze potential weaknesses and margins of error before making an investment.
V2V communication enables a plethora of cooperative applications aimed at reducing road hazard situations as well as enhancing traffic efficiency and individual driving comfort, expanding therewith the boundaries of Advanced Driver Assistance Systems (ADAS). These applications will be supported by IEEE 802.11p, a standard operating in the 5.9 GHz frequency band and adapted for the highly dynamic vehicular environment.
The focus of this work is V2V safety applications, which have already gained a major attention from the industry, academia, as well as standardization bodies. Being a subject of wireless communication the performance of V2V applications directly depends on the communication link quality and the packet distribution pattern. Therefore, the main purpose of this thesis is to develop an effective communication link reliability assessment method and analyze to what extent V2V communication is feasible to satisfy the reliability requirements of safety applications. Furthermore, we investigate the effectiveness of the proposed assessment method when applied for real-time communication link reliability prediction.
In particular, in this work we establish the link between classical network performance metrics and specific application reliability requirements and derive a set of advanced assessment metrics. Afterwards, we investigate through these metrics how different environmental factors affect application reliability based on the measurement data, which was obtained in elaborated real-world measurement campaigns and in different non-line-of-sight scenarios. Using the suggested metrics further in this work
we additionally analyze the achievable application reliability of the V2V safety applications in congested network scenarios through the simulation study. Based on these results we also define the most favorable combinations of the network parameters to support reliable operation of these applications.
Finally, in this thesis we examine to what extent the suggested metrics are suitable for applications while operating in real time. We develop and implement two frameworks for prediction of the communication link reliability, based on the data that was obtained over the 4.5 months of the simTD project field trials. Furthermore, we apply both frameworks to other measurement data, which was obtained outside the simTD project and assess the effectiveness of both frameworks under independent realistic
conditions.
Comprehensive digitization leads to new chal-lenges because of cybercrime and related security countermeasures. There is no doubt that this will fundamentally affect our lives and is leading to an increase in the importance of information security (IS). However, technology solutions alone are not sufficient to ensure IS countermeasures. The human side of security is important to protect organizational assets like user information and systems. The paper illustrates these relationships in terms of information security awareness (ISA), examining its goals and the factors influencing it through the systematic analysis and review of scientific literature and the transfer of scientific knowledge for practical purposes. We reviewed the publications of leading academic journals in the field of IS over the past decade.
While online information systems and platforms are being increasingly used, user expectations or the specific demands that come out of the usage context have received scant attention in previous developments. Therefore a finely structured, analytical instrument for evaluating information artefacts with specific emphasis on actors and usage was implemented in the Moodle learning platform for Moodle course room evaluation and tested with different student groups. Some surprising results came out of the discussion between the instructor and students. Moreover, this instrument, TEDS*MOODLE, can be scaled and flexibly customized and thus also integrated into existing e-government services and administrative networks.