•A LinearSVM model was able to extract e-mail sentiment with a mean AUC of 0.896.•The model could also predict sentiment for e-mail responses with a mean AUC of 0.805.•The results suggests ...possibilities for improved customer support mangement processes.
Customer support is important to corporate operations, which involves dealing with disgruntled customer and content customers that can have different requirements. As such, it is important to quickly extract the sentiment of support errands. In this study we investigate sentiment analysis in customer support for a large Swedish Telecom corporation. The data set consists of 168,010 e-mails divided into 69,900 conversation threads without any sentiment information available. Therefore, VADER sentiment is used together with a Swedish sentiment lexicon in order to provide initial labeling of the e-mails. The e-mail content and sentiment labels are then used to train two Support Vector Machine models in extracting/classifying the sentiment of e-mails. Further, the ability to predict sentiment of not-yet-seen e-mail responses is investigated. Experimental results show that the LinearSVM model was able to extract sentiment with a mean F1-score of 0.834 and mean AUC of 0.896. Moreover, the LinearSVM algorithm was also able to predict the sentiment of an e-mail one step ahead in the thread (based on the text in the an already sent e-mail) with a mean F1-score of 0.688 and the mean AUC of 0.805. The results indicate a predictable pattern in e-mail conversation that enables predicting the sentiment of a not-yet-seen e-mail. This can be used e.g. to prepare particular actions for customers that are likely to have a negative response. It can also provide feedback on possible sentiment reactions to customer support e-mails.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Influential users play an important role in online social networks since users tend to have an impact on one other. Therefore, the proposed work analyzes users and their behavior in order to identify ...influential users and predict user participation. Normally, the success of a social media site is dependent on the activity level of the participating users. For both online social networking sites and individual users, it is of interest to find out if a topic will be interesting or not. In this article, we propose association learning to detect relationships between users. In order to verify the findings, several experiments were executed based on social network analysis, in which the most influential users identified from association rule learning were compared to the results from Degree Centrality and Page Rank Centrality. The results clearly indicate that it is possible to identify the most influential users using association rule learning. In addition, the results also indicate a lower execution time compared to state-of-the-art methods.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
The evidence that burglaries cluster spatio-temporally is strong. However, research is unclear on whether clustered burglaries (repeats/near-repeats) should be treated as qualitatively different ...crimes compared to spatio-temporally unrelated burglaries (non-repeats). This study, therefore, investigated if there were differences in modus operandi-signatures (MOs, the habits and methods employed by criminals) between near-repeat and non-repeat burglaries across 10 Swedish cities, as well as whether MO-signatures can aid in predicting if a burglary is classified as a near-repeat or a non-repeat crime. Data consisted of 5744 residential burglaries, with 137 MO features characterizing each case. Descriptive data of repeats/non-repeats is provided together with Wilcoxon tests of MO-differences between crime pairs, while logistic regressions were used to train models to predict if a crime scene was classified as a near-repeat or a non-repeat crime. Near-repeat crimes were rather stylized, showing heterogeneity in MOs across cities, but showing homogeneity within cities at the same time, as there were significant differences between near-repeat and non-repeat burglaries, including subgroups of features, such as differences in mode of entering, target selection, types of goods stolen, as well the traces that were left at the crime scene. Furthermore, using logistic regression models, it was possible to predict near-repeat and non-repeat crimes with a mean F1-score of 0.8155 (0.0866) based on the MO. Potential policy implications are discussed in terms of how data-driven procedures can facilitate analysis of spatio-temporal phenomena based on the MO-signatures of offenders, as well as how law enforcement agencies can provide differentiated advice and response when there is suspicion that a crime is part of a series as opposed to an isolated event.
As machine learning and AI continue to rapidly develop, and with the ever-closer end of Moore’s law, new avenues and novel ideas in architecture design are being created and utilized. One avenue is ...accelerating AI as close to the user as possible, i.e., at the edge, to reduce latency and increase performance. Therefore, researchers have developed low-power AI accelerators, designed specifically to accelerate machine learning and AI at edge devices. In this paper, we present an overview of low-power AI accelerators between 2019–2022. Low-power AI accelerators are defined in this paper based on their acceleration target and power consumption. In this survey, 79 low-power AI accelerators are presented and discussed. The reviewed accelerators are discussed based on five criteria: (i) power, performance, and power efficiency, (ii) acceleration targets, (iii) arithmetic precision, (iv) neuromorphic accelerators, and (v) industry vs. academic accelerators. CNNs and DNNs are the most popular accelerator targets, while Transformers and SNNs are on the rise.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
Network anomaly detection for critical infrastructure supervisory control and data acquisition (SCADA) systems is the first line of defense against cyber-attacks. Often hybrid methods, such as ...machine learning with signature-based intrusion detection methods, are employed to improve the detection results. Here an attempt is made to enhance the support vector-based outlier detection method by leveraging behavioural attribute extension of the network nodes. The network nodes are modeled as graph vertices to construct related attributes that enhance network characterisation and potentially improve unsupervised anomaly detection ability for SCADA network. IEC 104 SCADA protocol communication data with good domain fidelity is utilised for empirical testing. The results demonstrate that the proposed approach achieves significant improvements over the baseline approach (average
F
1
score increased from 0.6 to 0.9, and Matthews correlation coefficient (MCC) from 0.3 to 0.8). The achieved outcome also surpasses the unsupervised scores of related literature. For critical networks, the identification of attacks is indispensable. The result shows an insignificant missed-alert rate (
0.3
%
on average), the lowest among related works. The gathered results show that the proposed approach can expose rouge SCADA nodes reasonably and assist in further pruning the identified unusual instances.
We present a method, including tool support, for bibliometric mining of trends in large and dynamic research areas. The method is applied to the machine learning research area for the years 2013 to ...2022. A total number of 398,782 documents from Scopus were analyzed. A taxonomy containing 26 research directions within machine learning was defined by four experts with the help of a Python program and existing taxonomies. The trends in terms of productivity, growth rate, and citations were analyzed for the research directions in the taxonomy. Our results show that the two directions, Applications and Algorithms, are the largest, and that the direction Convolutional Neural Networks is the one that grows the fastest and has the highest average number of citations per document. It also turns out that there is a clear correlation between the growth rate and the average number of citations per document, i.e., documents in fast-growing research directions have more citations. The trends for machine learning research in four geographic regions (North America, Europe, the BRICS countries, and The Rest of the World) were also analyzed. The number of documents during the time period considered is approximately the same for all regions. BRICS has the highest growth rate, and, on average, North America has the highest number of citations per document. Using our tool and method, we expect that one could perform a similar study in some other large and dynamic research area in a relatively short time.
Law enforcement agencies, as well as researchers rely on temporal analysis methods in many crime analyses, e.g., spatio-temporal analyses. A number of temporal analysis methods are being used, but a ...structured comparison in different configurations is yet to be done. This study aims to fill this research gap by comparing the accuracy of five existing, and one novel, temporal analysis methods in approximating offense times for residential burglaries that often lack precise time information. The temporal analysis methods are evaluated in eight different configurations with varying temporal resolution, as well as the amount of data (number of crimes) available during analysis. A dataset of all Swedish residential burglaries reported between 2010 and 2014 is used (N = 103,029). From that dataset, a subset of burglaries with known precise offense times is used for evaluation. The accuracy of the temporal analysis methods in approximating the distribution of burglaries with known precise offense times is investigated. The aoristic and the novel aoristic e x t method perform significantly better than three of the traditional methods. Experiments show that the novel aoristic e x t method was most suitable for estimating crime frequencies in the day-of-the-year temporal resolution when reduced numbers of crimes were available during analysis. In the other configurations investigated, the aoristic method showed the best results. The results also show the potential from temporal analysis methods in approximating the temporal distributions of residential burglaries in situations when limited data are available.
Non-Hodgkin lymphomas of the hypothalamus and pituitary are rare. They usually remain clinically silent until onset of compressive features affecting surrounding structures. When symptomatic, ...patients most commonly present with diabetes insipidus, headaches, ophthalmoplegia and/or bilateral hemianopia. We report a case of a 67-year-old Caucasian female with a history of B-cell lymphoma in complete remission. She presented with left oculomotor nerve palsy and was subsequently found to have a sellar/suprasellar mass lesion on MRI. Alongside hypocortisolism and hypogonadotropic hypogonadism, she developed transient diabetes insipidus during her illness. Her clinical course was characterized by rapid intracranial progression of the sellar mass. MR spectroscopy suggested a diagnosis of lymphoma. Diagnostic biopsy confirmed high-grade diffuse large B-cell CNS lymphoma; this changed the definitive management from surgical excision to chemotherapy. Despite treatment, she succumbed to her illness within 7 months of initial presentation. This case highlights the aggressive nature of CNS lymphomas and the need for a high index of suspicion in an unusual presentation of sellar/suprasellar mass lesions.
Novel imaging techniques such as MR spectroscopy might help to differentiate some brain tumours from pituitary macroadenomas, but these are not diagnostic.Tissue diagnosis with biopsy and histopathology is the gold standard for deciding management of pituitary fossa mass lesions with atypical presentation.
Clinically significant cytomegalovirus (CMV) reactivation is not uncommon in patients with severe immunodeficiency secondary to underlying medical disorders or following aggressive immunosuppressive ...therapy. However, it is less frequently found in patients with low-grade haematological malignancies after nonintensive chemotherapy. We treated a patient at our centre for stage IVB follicular lymphoma with standard chemotherapy who successively developed CMV colitis associated with a CMV viral load of >3 million copies/ml. Four lines of antiviral treatment were necessary to obtain biochemical remission with undetectable CMV levels, with an initially insufficient response to valganciclovir despite therapeutic pre- and posttreatment levels. Subsequently, our patient also developed an infection with Pneumocystis jirovecii pneumonia (PJP) as further evidence of severe immune compromise. This case report demonstrates the importance of including investigations for less common sources of infection when confronted with a patient with a low-grade haematological malignancy and a pyrexia of unknown origin.
Full text
Available for:
FZAB, GIS, IJS, IZUM, KILJ, NLZOH, NUK, OILJ, PILJ, PNG, SAZU, SBCE, SBMB, UL, UM, UPUK
Autoimmune haemolytic anaemia is not a well-recognised complication of sarcoidosis. We describe the case of a 30-year-old female who presented with acute warm haemolytic anaemia and widespread ...lymphadenopathy. Sarcoidosis was diagnosed on lymph node biopsy and further investigation. The haemolytic anaemia responded only to a high dose of steroids. Evidence regarding treatment of steroid refractory autoimmune haemolysis secondary to sarcoidosis is lacking. Based on the emergent evidence that both disorders share common immunopathogenic mechanisms involving Th1 and Th17 lymphocytes, our patient was given rituximab and mycophenolate mofetil to successfully suppress the haemolysis and sarcoid activity.
Full text
Available for:
FZAB, GIS, IJS, IZUM, KILJ, NLZOH, NUK, OILJ, PILJ, PNG, SAZU, SBCE, SBMB, UL, UM, UPUK